ISSN (ONLINE) : 2045 -8711 ISSN (PRINT) : 2045 -869X
INTERNATIONAL JOURNAL OF INNOVATIVE TECHNOLOGY & CREATIVE ENGINEERING JUNE 2018 VOL- 8 NO-6
@IJITCE Publication
INTERNATIONAL JOURNAL OF INNOVATIVE TECHNOLOGY AND CREATIVE ENGINEERING (ISSN:2045-8711) VOL.8 NO.6 JUNE 2018
UK: Managing Editor International Journal of Innovative Technology and Creative Engineering 1a park lane, Cranford London TW59WA UK E-Mail: editor@ijitce.co.uk Phone: +44-773-043-0249 USA: Editor International Journal of Innovative Technology and Creative Engineering Dr. Arumugam Department of Chemistry University of Georgia GA-30602, USA. Phone: 001-706-206-0812 Fax:001-706-542-2626 India: Editor International Journal of Innovative Technology & Creative Engineering Dr. Arthanariee. A. M Finance Tracking Center India 66/2 East mada st, Thiruvanmiyur, Chennai -600041 Mobile: 91-7598208700
www.ijitce.co.uk
INTERNATIONAL JOURNAL OF INNOVATIVE TECHNOLOGY AND CREATIVE ENGINEERING (ISSN:2045-8711) VOL.8 NO.6 JUNE 2018
www.ijitce.co.uk
IJITCE PUBLICATION
International Journal of Innovative Technology & Creative Engineering Vol.8 No.6 June 2018
www.ijitce.co.uk
www.ijitce.co.uk
INTERNATIONAL JOURNAL OF INNOVATIVE TECHNOLOGY AND CREATIVE ENGINEERING (ISSN:2045-8711) VOL.8 NO.6 JUNE 2018
From Editor's Desk Dear Researcher, Greetings! Research article in this issue discusses about motivational factor analysis. Let us review research around the world this month.
Quantum entanglement has left the realm of the utterly minuscule and crossed over to the just plain small. Two teams of researchers report that they have generated ethereal quantum linkages or entanglement, between pairs of jiggling objects visible with a magnifying glass or even the naked eye, if you have keen vision. It’s a first demonstration of entanglement over these artificial mechanical systems. Previously, scientists had entangled vibrations in two diamonds that were macroscopic, meaning they were visible to the naked eye. But this is the first time entanglement has been seen in macroscopic structures constructed by humans, which can be designed to meet particular technological requirements. Entanglement is a strange feature of quantum mechanics, through which two objects’ properties become intertwined. Measuring the properties of one object immediately reveals the state of the other, even though the duo may be separated by a large distance It has been an absolute pleasure to present you articles that you wish to read. We look forward to many more new technologies related research articles from you and your friends. We are anxiously awaiting the rich and thorough research papers that have been prepared by our authors for the next issue.
Thanks, Editorial Team IJITCE
www.ijitce.co.uk
INTERNATIONAL JOURNAL OF INNOVATIVE TECHNOLOGY AND CREATIVE ENGINEERING (ISSN:2045-8711) VOL.8 NO.6 JUNE 2018
Editorial Members Dr. Chee Kyun Ng Ph.D Department of Computer and Communication Systems, Faculty of Engineering,Universiti Putra Malaysia,UPMSerdang, 43400 Selangor,Malaysia. Dr. Simon SEE Ph.D Chief Technologist and Technical Director at Oracle Corporation, Associate Professor (Adjunct) at Nanyang Technological University Professor (Adjunct) at ShangaiJiaotong University, 27 West Coast Rise #08-12,Singapore 127470 Dr. sc.agr. Horst Juergen SCHWARTZ Ph.D, Humboldt-University of Berlin,Faculty of Agriculture and Horticulture,Asternplatz 2a, D-12203 Berlin,Germany Dr. Marco L. BianchiniPh.D Italian National Research Council; IBAF-CNR,Via Salaria km 29.300, 00015 MonterotondoScalo (RM),Italy Dr. NijadKabbaraPh.D Marine Research Centre / Remote Sensing Centre/ National Council for Scientific Research, P. O. Box: 189 Jounieh,Lebanon Dr. Aaron Solomon Ph.D Department of Computer Science, National Chi Nan University,No. 303, University Road,Puli Town, Nantou County 54561,Taiwan Dr. Arthanariee. A. M M.Sc.,M.Phil.,M.S.,Ph.D Director - Bharathidasan School of Computer Applications, Ellispettai, Erode, Tamil Nadu,India Dr. Takaharu KAMEOKA, Ph.D Professor, Laboratory of Food, Environmental & Cultural Informatics Division of Sustainable Resource Sciences, Graduate School of Bioresources,Mie University, 1577 Kurimamachiya-cho, Tsu, Mie, 514-8507, Japan Dr. M. Sivakumar M.C.A.,ITIL.,PRINCE2.,ISTQB.,OCP.,ICP. Ph.D. Project Manager - Software,Applied Materials,1a park lane,cranford,UK Dr. Bulent AcmaPh.D Anadolu University, Department of Economics,Unit of Southeastern Anatolia Project(GAP),26470 Eskisehir,TURKEY Dr. SelvanathanArumugamPh.D Research Scientist, Department of Chemistry, University of Georgia, GA-30602,USA.
Review Board Members Dr. Paul Koltun Senior Research ScientistLCA and Industrial Ecology Group,Metallic& Ceramic Materials,CSIRO Process Science & Engineering Private Bag 33, Clayton South MDC 3169,Gate 5 Normanby Rd., Clayton Vic. 3168, Australia Dr. Zhiming Yang MD., Ph. D. Department of Radiation Oncology and Molecular Radiation Science,1550 Orleans Street Rm 441, Baltimore MD, 21231,USA Dr. Jifeng Wang Department of Mechanical Science and Engineering, University of Illinois at Urbana-Champaign Urbana, Illinois, 61801, USA Dr. Giuseppe Baldacchini ENEA - Frascati Research Center, Via Enrico Fermi 45 - P.O. Box 65,00044 Frascati, Roma, ITALY. Dr. MutamedTurkiNayefKhatib Assistant Professor of Telecommunication Engineering,Head of Telecommunication Engineering Department,Palestine Technical University (Kadoorie), TulKarm, PALESTINE.
www.ijitce.co.uk
INTERNATIONAL JOURNAL OF INNOVATIVE TECHNOLOGY AND CREATIVE ENGINEERING (ISSN:2045-8711) VOL.8 NO.6 JUNE 2018 Dr.P.UmaMaheswari Prof &Head,Depaartment of CSE/IT, INFO Institute of Engineering,Coimbatore. Dr. T. Christopher, Ph.D., Assistant Professor &Head,Department of Computer Science,Government Arts College(Autonomous),Udumalpet, India. Dr. T. DEVI Ph.D. Engg. (Warwick, UK), Head,Department of Computer Applications,Bharathiar University,Coimbatore-641 046, India. Dr. Renato J. orsato Professor at FGV-EAESP,Getulio Vargas Foundation,São Paulo Business School,RuaItapeva, 474 (8° andar),01332-000, São Paulo (SP), Brazil Visiting Scholar at INSEAD,INSEAD Social Innovation Centre,Boulevard de Constance,77305 Fontainebleau - France Y. BenalYurtlu Assist. Prof. OndokuzMayis University Dr.Sumeer Gul Assistant Professor,Department of Library and Information Science,University of Kashmir,India Dr. ChutimaBoonthum-Denecke, Ph.D Department of Computer Science,Science& Technology Bldg., Rm 120,Hampton University,Hampton, VA 23688 Dr. Renato J. Orsato Professor at FGV-EAESP,Getulio Vargas Foundation,São Paulo Business SchoolRuaItapeva, 474 (8° andar),01332-000, São Paulo (SP), Brazil Dr. Lucy M. Brown, Ph.D. Texas State University,601 University Drive,School of Journalism and Mass Communication,OM330B,San Marcos, TX 78666 JavadRobati Crop Production Departement,University of Maragheh,Golshahr,Maragheh,Iran VineshSukumar (PhD, MBA) Product Engineering Segment Manager, Imaging Products, Aptina Imaging Inc. Dr. Binod Kumar PhD(CS), M.Phil.(CS), MIAENG,MIEEE HOD & Associate Professor, IT Dept, Medi-Caps Inst. of Science & Tech.(MIST),Indore, India Dr. S. B. Warkad Associate Professor, Department of Electrical Engineering, Priyadarshini College of Engineering, Nagpur, India Dr. doc. Ing. RostislavChoteborský, Ph.D. Katedramateriálu a strojírenskétechnologieTechnickáfakulta,Ceskázemedelskáuniverzita v Praze,Kamýcká 129, Praha 6, 165 21 Dr. Paul Koltun Senior Research ScientistLCA and Industrial Ecology Group,Metallic& Ceramic Materials,CSIRO Process Science & Engineering Private Bag 33, Clayton South MDC 3169,Gate 5 Normanby Rd., Clayton Vic. 3168 DR.ChutimaBoonthum-Denecke, Ph.D Department of Computer Science,Science& Technology Bldg.,HamptonUniversity,Hampton, VA 23688 Mr. Abhishek Taneja B.sc(Electronics),M.B.E,M.C.A.,M.Phil., Assistant Professor in the Department of Computer Science & Applications, at Dronacharya Institute of Management and Technology, Kurukshetra. (India). Dr. Ing. RostislavChotěborský,ph.d, Katedramateriálu a strojírenskétechnologie, Technickáfakulta,Českázemědělskáuniverzita v Praze,Kamýcká 129, Praha 6, 165 21
www.ijitce.co.uk
INTERNATIONAL JOURNAL OF INNOVATIVE TECHNOLOGY AND CREATIVE ENGINEERING (ISSN:2045-8711) VOL.8 NO.6 JUNE 2018 Dr. AmalaVijayaSelvi Rajan, B.sc,Ph.d, Faculty – Information Technology Dubai Women’s College – Higher Colleges of Technology,P.O. Box – 16062, Dubai, UAE Naik Nitin AshokraoB.sc,M.Sc Lecturer in YeshwantMahavidyalayaNanded University Dr.A.Kathirvell, B.E, M.E, Ph.D,MISTE, MIACSIT, MENGG Professor - Department of Computer Science and Engineering,Tagore Engineering College, Chennai Dr. H. S. Fadewar B.sc,M.sc,M.Phil.,ph.d,PGDBM,B.Ed. Associate Professor - Sinhgad Institute of Management & Computer Application, Mumbai-BangloreWesternly Express Way Narhe, Pune - 41 Dr. David Batten Leader, Algal Pre-Feasibility Study,Transport Technologies and Sustainable Fuels,CSIRO Energy Transformed Flagship Private Bag 1,Aspendale, Vic. 3195,AUSTRALIA Dr R C Panda (MTech& PhD(IITM);Ex-Faculty (Curtin Univ Tech, Perth, Australia))Scientist CLRI (CSIR), Adyar, Chennai - 600 020,India Miss Jing He PH.D. Candidate of Georgia State University,1450 Willow Lake Dr. NE,Atlanta, GA, 30329 Jeremiah Neubert Assistant Professor,MechanicalEngineering,University of North Dakota Hui Shen Mechanical Engineering Dept,Ohio Northern Univ. Dr. Xiangfa Wu, Ph.D. Assistant Professor / Mechanical Engineering,NORTH DAKOTA STATE UNIVERSITY SeraphinChallyAbou Professor,Mechanical& Industrial Engineering Depart,MEHS Program, 235 Voss-Kovach Hall,1305 OrdeanCourt,Duluth, Minnesota 55812-3042 Dr. Qiang Cheng, Ph.D. Assistant Professor,Computer Science Department Southern Illinois University CarbondaleFaner Hall, Room 2140-Mail Code 45111000 Faner Drive, Carbondale, IL 62901 Dr. Carlos Barrios, PhD Assistant Professor of Architecture,School of Architecture and Planning,The Catholic University of America Y. BenalYurtlu Assist. Prof. OndokuzMayis University Dr. Lucy M. Brown, Ph.D. Texas State University,601 University Drive,School of Journalism and Mass Communication,OM330B,San Marcos, TX 78666 Dr. Paul Koltun Senior Research ScientistLCA and Industrial Ecology Group,Metallic& Ceramic Materials CSIRO Process Science & Engineering Dr.Sumeer Gul Assistant Professor,Department of Library and Information Science,University of Kashmir,India Dr. ChutimaBoonthum-Denecke, Ph.D Department of Computer Science,Science& Technology Bldg., Rm 120,Hampton University,Hampton, VA 23688
www.ijitce.co.uk
INTERNATIONAL JOURNAL OF INNOVATIVE TECHNOLOGY AND CREATIVE ENGINEERING (ISSN:2045-8711) VOL.8 NO.6 JUNE 2018 Dr. Renato J. Orsato Professor at FGV-EAESP,Getulio Vargas Foundation,São Paulo Business School,RuaItapeva, 474 (8° andar)01332-000, São Paulo (SP), Brazil Dr. Wael M. G. Ibrahim Department Head-Electronics Engineering Technology Dept.School of Engineering Technology ECPI College of Technology 5501 Greenwich Road Suite 100,Virginia Beach, VA 23462 Dr. Messaoud Jake Bahoura Associate Professor-Engineering Department and Center for Materials Research Norfolk State University,700 Park avenue,Norfolk, VA 23504 Dr. V. P. Eswaramurthy M.C.A., M.Phil., Ph.D., Assistant Professor of Computer Science, Government Arts College(Autonomous), Salem-636 007, India. Dr. P. Kamakkannan,M.C.A., Ph.D ., Assistant Professor of Computer Science, Government Arts College(Autonomous), Salem-636 007, India. Dr. V. Karthikeyani Ph.D., Assistant Professor of Computer Science, Government Arts College(Autonomous), Salem-636 008, India. Dr. K. Thangadurai Ph.D., Assistant Professor, Department of Computer Science, Government Arts College ( Autonomous ), Karur - 639 005,India. Dr. N. Maheswari Ph.D., Assistant Professor, Department of MCA, Faculty of Engineering and Technology, SRM University, Kattangulathur, Kanchipiram Dt - 603 203, India. Mr. Md. Musfique Anwar B.Sc(Engg.) Lecturer, Computer Science & Engineering Department, Jahangirnagar University, Savar, Dhaka, Bangladesh. Mrs. Smitha Ramachandran M.Sc(CS)., SAP Analyst, Akzonobel, Slough, United Kingdom. Dr. V. Vallimayil Ph.D., Director, Department of MCA, Vivekanandha Business School For Women, Elayampalayam, Tiruchengode - 637 205, India. Mr. M. Moorthi M.C.A., M.Phil., Assistant Professor, Department of computer Applications, Kongu Arts and Science College, India PremaSelvarajBsc,M.C.A,M.Phil Assistant Professor,Department of Computer Science,KSR College of Arts and Science, Tiruchengode Mr. G. Rajendran M.C.A., M.Phil., N.E.T., PGDBM., PGDBF., Assistant Professor, Department of Computer Science, Government Arts College, Salem, India. Dr. Pradeep H Pendse B.E.,M.M.S.,Ph.d Dean - IT,Welingkar Institute of Management Development and Research, Mumbai, India Muhammad Javed Centre for Next Generation Localisation, School of Computing, Dublin City University, Dublin 9, Ireland Dr. G. GOBI Assistant Professor-Department of Physics,Government Arts College,Salem - 636 007 Dr.S.Senthilkumar Post Doctoral Research Fellow, (Mathematics and Computer Science & Applications),UniversitiSainsMalaysia,School of Mathematical Sciences, Pulau Pinang-11800,[PENANG],MALAYSIA. Manoj Sharma Associate Professor Deptt. of ECE, PrannathParnami Institute of Management & Technology, Hissar, Haryana, India RAMKUMAR JAGANATHAN Asst-Professor,Dept of Computer Science, V.L.B Janakiammal college of Arts & Science, Coimbatore,Tamilnadu, India
www.ijitce.co.uk
INTERNATIONAL JOURNAL OF INNOVATIVE TECHNOLOGY AND CREATIVE ENGINEERING (ISSN:2045-8711) VOL.8 NO.6 JUNE 2018 Dr. S. B. Warkad Assoc. Professor, Priyadarshini College of Engineering, Nagpur, Maharashtra State, India Dr. Saurabh Pal Associate Professor, UNS Institute of Engg. & Tech., VBS Purvanchal University, Jaunpur, India Manimala Assistant Professor, Department of Applied Electronics and Instrumentation, St Joseph’s College of Engineering & Technology, Choondacherry Post, Kottayam Dt. Kerala -686579 Dr. Qazi S. M. Zia-ul-Haque Control Engineer Synchrotron-light for Experimental Sciences and Applications in the Middle East (SESAME),P. O. Box 7, Allan 19252, Jordan Dr. A. Subramani, M.C.A.,M.Phil.,Ph.D. Professor,Department of Computer Applications, K.S.R. College of Engineering, Tiruchengode - 637215 Dr. SeraphinChallyAbou Professor, Mechanical & Industrial Engineering Depart. MEHS Program, 235 Voss-Kovach Hall, 1305 Ordean Court Duluth, Minnesota 55812-3042 Dr. K. Kousalya Professor, Department of CSE,Kongu Engineering College,Perundurai-638 052 Dr. (Mrs.) R. Uma Rani Asso.Prof., Department of Computer Science, Sri Sarada College For Women, Salem-16, Tamil Nadu, India. MOHAMMAD YAZDANI-ASRAMI Electrical and Computer Engineering Department, Babol"Noshirvani" University of Technology, Iran. Dr. Kulasekharan, N, Ph.D Technical Lead - CFD,GE Appliances and Lighting, GE India,John F Welch Technology Center,Plot # 122, EPIP, Phase 2,Whitefield Road,Bangalore – 560066, India. Dr. Manjeet Bansal Dean (Post Graduate),Department of Civil Engineering,Punjab Technical University,GianiZail Singh Campus,Bathinda -151001 (Punjab),INDIA Dr. Oliver Jukić Vice Dean for education,Virovitica College,MatijeGupca 78,33000 Virovitica, Croatia Dr. Lori A. Wolff, Ph.D., J.D. Professor of Leadership and Counselor Education,The University of Mississippi,Department of Leadership and Counselor Education, 139 Guyton University, MS 38677
www.ijitce.co.uk
INTERNATIONAL JOURNAL OF INNOVATIVE TECHNOLOGY AND CREATIVE ENGINEERING (ISSN:2045-8711) VOL.8 NO.6 JUNE 2018
Contents Application of Data Mining Methods in the An alysis of Different Attacks on Network Shilpa Srivastava, Dr.Mohit Gangwar ……………………………. [485] Framework for Opinion Mining Approach to Augment Education System Performance Amritpal Kaur, Harkiran Kaur ……………………………. [493] Emerging Prospects of e-Commerce through CRM practices in the modern Banking Industry John Paul .M & Chemmalar. A ……………………………. [498]
www.ijitce.co.uk
INTERNATIONAL JOURNAL OF INNOVATIVE TECHNOLOGY AND CREATIVE ENGINEERING (ISSN:2045-8711) VOL.8 NO.6 JUNE 2018
Application of Data Mining Methods in the Analysis of Different Attacks on Network Shilpa Srivastava M.Tech. Research Scholar, CSED, BERI, Bhopal, India Dr.Mohit Gangwar Principal/Professor (CSED), BERI, Bhopal, India E-mail: mohitgangwar@gmail.com Abstract- Many of us connect to Wireless Fidelity (Wi-Fi) without knowing what specific threats one is vulnerable. The list of vulnerabilities is large by nature, and most of these ignored by users. Computer networking has made collaboration necessary to both attackers and defenders. Phishing attacks combine technology and social engineering to gain access to restricted information. The most common phishing attacks today send mass email directing the victim to a web site of some perceived authority. This paper is focused on wireless network and phishing attacks. To analysis attacks on network signal we are applying different data mining algorithms like J48, random Forest and random Tree algorithms on network dataset of 3 years with 6 different attribute name “Company”, “Data Provider”, “Data Used”, “Date”, “Class”, & “Signal” from different telecom companies to achieve 95 to 99% accuracy with a false positive rate of 0.5-1.5% and modest false negatives. Thus, the comparative views shows that J48 algorithm for phishing detection achieves better performance as compared to random Forest and random Tree algorithm. Keywords- Phishing Attacks, J48, Random Forest, Random Tree, Confusion Matrix, Network Signal.
1. INTRODUCTION Phishing attacks combine technology and social engineering to gain access to restricted information. The most common phishing attacks today send mass email directing the victim to a web site of some perceived authority. These web sites typically spoof online banks, government agencies, electronic payment firms, and virtual marketplaces. The fraudulent web page collects information from the victim under the guise of “authentication," “security," or “account update." Some of these compromised hosts simply download malware onto clients rather than collect information directly [1]. Phishing is a type of deception designed to steal your valuable personal data, such as credit card numbers, passwords, account data, or other information.
Figure 1: Working Process of Phishing Attacks [1] 1.1. TYPES OF PHISHING ATTACK Type of Phishing attacks are as follow: 1.1.1 DECEPTIVE PHISHING Today most common method for phishing is deceptive email message. Some scam emails links are received by the recipients though email. The user not having awareness about that scam they click and signing on that website from where the scammer collect all confidential information of that user [1, 4, 8]. 1.1.2 MALWARE-BASED PHISHING It is scams that involve running malicious software on users' PCs. They also allow copying all sensitive information and echoed to other software. This can be entered via email attachment, and downloadable files from website. This kind of phishing generates with those users who are not always update their software application [1, 4, 9, 10]. 1.1.3
KEY LOGGERS AND SCREEN LOGGERS This is a variety of malware that track keyboard input and send sensitive information to the hacker via the Internet. This malware generate itself into user’s browsers as small utility programs that run automatically when browser is started [1, 4, 9, 10]. 1.1.4 SESSION HIJACKING It describes an attack where users' activities are monitored until they sign in to a target account or transaction. At that point the malicious software takes over and can undertake unauthorized actions, such as transferring funds, without the user's knowledge [1, 4, 9, 10].
485
INTERNATIONAL JOURNAL OF INNOVATIVE TECHNOLOGY AND CREATIVE ENGINEERING (ISSN:2045-8711) VOL.8 NO.6 JUNE 2018
1.1.5 WEB TROJANS It generate invisibly pop up when users logged in. They collect all sensitive information of user and transmit them to the phisher [1, 4, 9, 10].
better interest rates than other banks. Victims who use these sites to save or make more from interest charges are encouraged to transfer existing accounts and deceived into giving up their details [1, 4, 9, 10].
1.1.6 HOSTS FILE POISONING When a user types a URL to visit a website it must first be translated into an IP address before it's transmitted over the Internet. By "poisoning" the hosts file, hackers have a fake address transmitted, taking the user unintentionally to a fake website where their information can be stolen [1, 4, 9, 10].
1.2. ORGANIZATION OF PAPER RELATED WORK Section 1: Introduction-In this section we give brief introduction of phishing attacks and their classification. Section 2: Related Work-In this section we studied various papers related to the previous classification method and algorithm. Section 3: Problem Identification & Problem Description-In this section we have described the problems of phishing attacks and its description. Section 4: Proposed Data mining Models-In this section we have applied different data mining models to analysis comparative results. Section 5: Simulation and Implementation-In this section we have discussed the implementation of applied data mining models, Section 6: Results & Discussion-In this section we have discuss analysis and results. Section 7: Conclusion-In this section we describe the conclusion.
1.1.7 SYSTEM RECONFIGURATION ATTACKS It modifies settings on a user's PC for malicious purposes. For example it modify favorites website to ‘look alike’ website for example: a bank website URL may be changed from "bankofabc.com" to "bancofabc.com" [1, 4, 9, 10]. 1.1.8. DATA THEFT Data theft is a widely used approach to business following. By stealing confidential communications, design documents, legal opinions, and employee related records, etc., thieves profit from selling to those who may want to embarrass or cause economic damage or to competitors [1, 4, 9, 10]. 1.1.9. DNS-BASED PHISHING Pharming is the term given to hosts file modification or Domain Name System (DNS)-based phishing. With a pharming scheme, hackers change the host’s files or domain name system so that requests for URLs or name service return a fake address and similar communications are directed to a fake site. The result: users are not aware that the website where they are entering confidential information is controlled by hackers and is probably not even in the same country as the legal website [1, 4, 9, 10]. 1.1.10. CONTENT-INJECTION PHISHING It is describing the situation where hackers replace part of the content of a legal site with false content which is designed to mislead or misdirect the user into giving up their confidential information to the hacker [1,4,9,10]. 1.1.11. MAN-IN-THE-MIDDLE PHISHING It is harder to detect than many other forms of phishing. In these attacks hackers is present between the user and the legal website or system. They record the information being entered but continue to pass it on so that users' transactions are not affected. Later they use the information or credentials collected when the user is not active on the system [1, 4, 9, 10]. 1.1.12. SEARCH ENGINE PHISHING Phishers create websites with some attractive look and indexed it in search engine as a legal website. Users find the sites while searching normally for products or services and are fooled into giving up their information. For example, scammers provide false banking sites which offering lower credit costs or
2. RELATED WORK One of the first mass attacks on embedded software was performed by the Chernobyl virus in [5]. The objective of this malware is purely obliteration. It attempts to erase the hard disk and overwrite the BIOS (Basic input and output service) at specified dates. Cell phones have also become targets for worms with the first reports in the wild in [6], the same author in [7] predicted infectious malware for the Linksys line of home routers, switches and wireless access points. Adelstein, Stillerman and Kozen identify nondestructive malware in Open Firmware boot platforms as a threat. To assure portability, parts of the boot software are written in the stack based language, Forth, and these scripts are executed via an interpreter. They propose a code analyzer the checks for malicious code at load time and prevent aged code from running. Arbaugh, Farber, and Smith implement a cryptographic access control system, AEGIS, to ensure that only sanctioned bootstrapping firmware can be installed on the host platform [3]. This study explores a variant of email based phishing, where distribution occurs through online market places and hardware is “spoofed" by maliciously compromising its embedded software. Our central example, the malicious home network router, steals information not only by passive eavesdropping, but by Pharming or DNS (Domain name Server or System) spoofing [2]. Browser toolbars at potential phishing web sites using a mixture of link analysis, content analysis, reputation databases, and IP (Internet Protocol) address information. Spoof Guard does two rounds of checks. If either of these tests fails, a second round examines images and form boxes to determine if the page semantically represents a request for information (e.g. login, credit card, etc.) Another system, PwdHash, generates per site passwords by hashing domain name concatenated to the user password. When the domain names differ, the resulting string does not reveal a usable passphrase. Pharming attacks defeat both of these tactics because they assume correct name resolution. The Net craft toolbar claims defends against Pharming attacks since it reveals the geographic location of the
486
INTERNATIONAL JOURNAL OF INNOVATIVE TECHNOLOGY AND CREATIVE ENGINEERING (ISSN:2045-8711) VOL.8 NO.6 JUNE 2018
server. While this can raise suspicion, it does not provide a strong defense. Criminal networks have commoditized zombie machines with prices ranging from $0.02 to $0.10 per unit; attackers can choose plausible locations for their hosts if this method ever becomes an effective defense [7]. Phishing is some kind of criminal activity employing in both technical and social engineering to steal personal information by surfing and visiting fake web pages which is look like as same as a legal website of bank and company and ask the user to enter personal information like user name, password, credit card number, etc. This paper main goal is to investigate the potential of data mining technique to detecting the complex problem of phishing website in order to help all users being hacked by stealing their personal information and password. Experimentations against phishing data sets and using different common associative classification algorithms (MCAR and CBA) and traditional learning approaches have been conducted with reference to classification accuracy. The results show that the MCAR and CBA algorithms outperformed SVM and algorithms [30]. Phishing attacks are one of the trending cyber-attacks that apply socially engineered messages that are communicated to people from professional hackers aiming at fooling users to reveal their sensitive information; the most popular communication channel to those messages is through users’ emails. This paper presents an intelligent classification model for detecting phishing emails using knowledge discovery, data mining and text processing techniques. The pre-processing phase is enhanced by applying text stemming and WordNet ontology to enrich the model with word synonyms. The model applied the knowledge discovery procedures using five popular classification algorithms and achieved a notable enhancement in classification accuracy; 99.1% accuracy was achieved using the Random Forest algorithm and 98.4% using J48, which is to our knowledge, the highest accuracy rate for an accredited dataset. This paper presents a comparative study with similar proposed classification techniques [21]. 3. PROBLEM DESCRIPTION AND PROBLEM IDENTIFICATION On the basis of previous paper and related works networks are vulnerable for attacks. So, we have identified problem on the bases of vulnerabilities from previous papers are as follow [22]: When discussing network security, the three common terms used are as follows: ■ Vulnerability- It is having a possibility to attack or harmed network or device. This includes routers, switches, desktops, servers, and even security devices themselves [22]. ■ Threats- A threats is something which has potential to harm or damage the computer system or network [4, 22]. ■ Attacks- The threats use a variety of tools, scripts, and programs to launch attacks against networks and network devices [22, 27]. 3.1. PROBLEM DESCRIPTION On the basis of previous paper and identification of different attacks for networks, Networks are not secure and easily accessible by the attackers, various data mining
techniques are applied in detection and analysis of mobile networks [26-29]. In this work we are collected three year of network data from different telecom companies to identify the passive attacks on network signals either the network is active or not active. Table 1 & 2 represents different network provider companies with different parameters name Data provided in GB, Data used in GB, Data provided duration (1 month), Class (Active & Not Active) and Signal (Yes & No). Network provider companies are: TABLE 1: DIFFERENT MOBILE SERVICE PROVIDERS Sr. No. Mobile Service Provider 1. Idea [31] 2. Docomo [32] 3. Airtel [33] 4. Bsnl [34] 5. Jio [35] 6. Vodaphone [36] 7. Relaince [37] In Table 2 shows demonstration of dataset in that row represents the Network signal companies and the column represents their respective parameters. TABLE 2: NETWORK DATA SET Company
Data Provided ( GB)
Data used (GB)
Idea
25
20
Docomo
30
20
Airtel
28
20
Bsnl
30
11
Jio
59
57
Vodafone
39
34
Reliance
28
25
Idea
25
17
Date 15-Jan2015 15-Jan2015 15-Jan2015 15-Jan2015 15-Jan2015 15-Jan2015 15-Jan2015 15-Feb2015
Class
Sig nal
active
Yes
Inactive
No
active
Yes
Inactive
No
active
Yes
active
No
active
Yes
Inactive
No
4. PROPOSED DATA MINING MODELS In this Research Work various supervised classification algorithm techniques were applied to create different data mining models for detection and analysis of network signal data. 1. J48 Algorithm [23] 2. Random Forest Algorithm [24] 3. Random Tree Algorithm [25] 4.1. J48 ALGORITHM J48 algorithm examine the normalization information gain that result to choose the attribute for splitting data, This splitting is stop if all instances in a subset belong to the same class. The first level of tree is a single header node. It is just a pointer node to its children. The second level of the tree has 2 sub trees labeled from 1 to2.
487
INTERNATIONAL JOURNAL OF INNOVATIVE TECHNOLOGY AND CREATIVE ENGINEERING (ISSN:2045-8711) VOL.8 NO.6 JUNE 2018
4.2. RANDOM FOREST First Random Forest algorithm is a supervised classification algorithm, we can see it from its name, which is to create a forest by some way and make it random. There is a direct relationship between the numbers of trees in the forest by some way and make it random. There is a direct relationship between the number of trees in the forest and the result it can get the larger the number of trees, the more accurate the result. But one thing to note is that creating the forest is not the same as constructing the decision with information gain or gain index approach [24]. 4.3. RANDOM TREE It can be used with data in a distribute environment and requires that you have a connection to analytic Server. Using this node, you build an ensemble model that consists of multiple decision trees. The random Tree hub can be utilized with the information in an appropriated domain to construct a gathering model that comprises of various choices trees [25]. 4.4. PROPOSED MODELS
4.6. ANALYSIS OF PRECISION, RECALL, ACCURACY BY USING DIFFERENT DATA MINING MODELS Analysis, Precision, Recall, F-Measure, & Accuracy is calculated using following formulas [21]. Precision = True Positive / (True Positive +False Positive) Recall = True Positive / (True Positive +False Positive) F1 = 2(Precision*Recall)/ (Precision + Recall) Accuracy = (True Positive +True Negative) (True Positive +True Negative +False Positive + False Negative) 4.7. TOOLS AND SYSTEM DESCRIPTION We are using creative models and to perform analysis of WEKA to perform our analysis. We required some hardware and software interface for the purpose of our simulation. Brief description is as shown in Table 3. TABLE 3: REQUIRED HARDWARE AND SOFTWARE Hardware Required System Hard disk RAM Software Required Operating System Tool Data Sheet
Figure 2: Flow Diagram for the Proposed Work Flow Which Is Executed Over Weka Tool In Figure 2 shown the diagram for the proposed work flow which executed over Weka tool in this network signal data is extracted from the resources in next step parameter is initialized after preprocessing noise is removed from data after this applying classification approach (J48,Ramdom Forest and Random Tree) over refined dataset the comprised parameter is computed. 4.5. ACCURACY AND EFFICIENCY CALCULATION Now, simply diagonal elements of the confusion matrix represent the true positive values and the rest of elements represent false positive values. Different operative characteristics are defined as follows: True Positive (TP) = When test outcome is positive and condition is also positive then the situation is called as True Positive Values. False Positive (FP) = When test outcome is positive and condition is negative then the situation is called as False Positive Values. True Negative (TN) = When test outcome is negative and condition is also negative then the situation is called as False negative Values. False Negative (FN) = When test outcome is negative and condition is positive then the situation is called as False positive Values.
Intel core I3 1Tb 4 GB Windows7 WEKA Excel File
4.8. WEKA TOOL In the work WEKA tool is used for the analysis and evaluation.
FIGURE 3: WEKA TOOL INITIALIZATION: STARTING WEKA GUI In the above Figure 3, a WEKA tool Initialization is presented where Explorer, Experimenter, and other Knowledge framework is shown. This figure shows the start page of weka tool, which we have used to analysis.
488
INTERNATIONAL JOURNAL OF INNOVATIVE TECHNOLOGY AND CREATIVE ENGINEERING (ISSN:2045-8711) VOL.8 NO.6 JUNE 2018
5. SIMULATION AND IMPLEMENTATION Here we collect three year of network data from different telecom companies to identify the passive attacks on network signals either the network is active or not active. In table 7 shows demonstration of dataset in that row represents the Network signal companies and the column represents their respective parameters. Comp any Idea Docom o Airtel Bsnl Jio Vodafo ne Relianc e Idea
TABLE 4: NETWORK DATA SET DataProvide Dataused Clas d ( GB) (GB) Date s 15-Janactiv 25 20 2015 e 15-JanInact 30 20 2015 ive 15-Janactiv 28 20 2015 e 15-JanInact 30 11 2015 ive 15-Janactiv 59 57 2015 e 15-Janactiv 39 34 2015 e 15-Janactiv 28 25 2015 e 15-Feb- Inact 25 17 2015 ive
Information gain is the mathematical tool that algorithm J48 has used to decide, in each node, which variable fits better in terms variable prediction. In this algorithm correctly classified instances are 235 out of 252 instances and incorrectly classified instances are 17 out of 252 instances. The percentage of accuracy in J48 is 93.26% to detect network signals. TP, FP, TN using active and not active signals. TABLE 6: CONFUSION MATRIX FOR RANDOM FOREST
Sig nal
A
Idea Docomo Airtel Bsnl Jio Vodaphone Relaince
Classified as
Yes
1 Yes 24 No From the above Table 6 confusion matrix true positive for class a=yes is 201 while false positive is 1 where as class b= No is 34 while false negative is 16.
No
5.2. RANDOM FOREST ANALYSIS VISUALIZATION
Yes No
Yes No Yes No
Above Table 4 showing three year of network data from different telecom companies to identify the passive attacks on network signals either the network is active or not active. The table represents different network provider companies with different parameters name Data provided in GB, Data used in GB, Data provided duration (1 month), Class (Active & Not Active) and Signal (Yes & No). TABLE 5: ATTRIBUTES AND ITS DATA TYPES Attributes
B
202 16
Data Type Categorical(Active, Not Active) Categorical(Active, Not Active) Categorical(Active, Not Active) Categorical(Active, Not Active) Categorical(Active, Not Active) Categorical(Active, Not Active) Categorical(Active, Not Active)
5.1. J48 Analysis Visualization
FIGURE 5: APPLYING RANDOM FOREST VISUALIZATION ON CLASSIFY ATTRIBUTE TABLE 7: CONFUSION MATRIX FOR RANDOM FOREST A 200 19
B 2 31
Classified as Yes No
From the above Table 7 confusion matrix true positive for class a=yes is 200 while false positive is 2 where as class b= No is 31 while false negative is 19. 5.3. RANDOM TREE ANALYSIS VISUALIZATION
FIGURE 4: THE ANALYSIS VISUALIZATION BY J48 OF DETAILED ACCURACY BY CLASS 489
INTERNATIONAL JOURNAL OF INNOVATIVE TECHNOLOGY AND CREATIVE ENGINEERING (ISSN:2045-8711) VOL.8 NO.6 JUNE 2018 Dataset
Algorithm
TABLE 8: CONFUSION MATRIX FOR RANDOM TREE A 191 19
B 11 31
Classified as Yes No
6. RESULTS AND DISCUSSIONS This section presents the results that the proposed classification model achieved by applying the three proposed classification algorithms to the features extracted from the data set of 252 network signal dataset. The generated features were fed to the three classifiers, namely J48, Random Forest& Random Tree. To avoid over fitting, we used 10-fold cross validation technique which uses 0.9 of the training data set as data for training the algorithm and the remaining 0.1 of training data set for testing purposes, and repeat this division of the data set for training and testing for 10 times. The experiments were conducted using the open source WEKA data mining software. The results were evaluated using the performance metrics discussed in the previous section. Table 9 depicts the weighted average of classification results for each of the algorithms. The results show that our model achieves high accuracy rates in classifying phishing on network signals, and outperforms similar proposed classification schemes as we will explain in the next section, thanks to the proposed preprocessing phase and feature reduction and evaluation process in the proposed model. The best results were achieved by the J48 is 93.26% to detect network signals. TABLE 9: CLASSIFICATION OF DATA MINING MODELS D.M Model s
TP Rat e
FP Rat e
Precisio n
Recal l
FMeasur e
J48
0.93 3 0.91 7
0.25 7 0.30 7
0.935
0.933
0.928
0.918
0.917
0.91
0.88 1
0.31 5
0.876
0.881
0.877
Rando m Forest Rando m Tree
RO C Are a 0.80 2 0.83 3 0.76 1
Network Signals Number of instance s is 252
Precision %
Recall %
FMeasure%
Accuracy%
J48
92.6
99.5
95.9
93.25
RF
91.3
98.6
94.5
91.67
RT
90.5
94.6
92.7
88.09
TABLE 10: COMPARATIVE ANALYSIS BETWEEN EXISTING AND PROPOSED ALGORITHM IN PERCENTAGE 6.2 A Graphical Comparison Analysis Of Classification Approach In the Figure 7, a graphical analysis of computation parameter, with the data set is computed. Comparative view of result shows that in terms of accuracy J48-93.25% is the best.
FIGURE 7: SHOWING THE GRAPHICAL REPRESENTATION OF ANALYSIS. RESULTS FOR APPLIED ALGORITHMS 6.3. Comparative Analysis A set of proposed studies are found in the literature of phishing email detection using data mining techniques, in this section we compare our proposed model with a set of previously proposed models for phishing detection. Table 11 summarizes a set of three previous related works along with the classification algorithm(s) used and the accuracy of the classification results, the results are visualized in Figure 8.
6.1. COMPARATIVE ANALYSIS OF PROPOSED ALGORITHM Information gain is the mathematical tool that algorithm J48 has used to decide, in each node, which variable fits better in terms variable prediction. In this algorithm correctly classified instances are 235 out of 252 instances and incorrectly classified instances are 17 out of 252 instances. The percentage of accuracy in J48 is 93.26% to detect network signals TP, FP, TN & FN using active and not active signals. Table 10 is showing comparative results of applied algorithms.
490
TABLE 11: COMPARISON OF OUR APPROACH WITH PREVIOUS WORK Paper Reference [19] [20] [21]
Our Approach
Classification
Accuracy
Random Forest J48+SVM Decision Tree, Random Forest and SVM J48,Random Forest and Random Tree
0.87 0.89 0.91
0.93
INTERNATIONAL JOURNAL OF INNOVATIVE TECHNOLOGY AND CREATIVE ENGINEERING (ISSN:2045-8711) VOL.8 NO.6 JUNE 2018
FIGURE 8: COMPARISON OF OUR APPROACH ACCURACY WITH RELATED WORK
The study in [19] used a feature vector of 47 features extracted from the same data sets of Nazario and Spam Assassin corpus, using Random Forest algorithm for training the classification model. Their model achieved 0.87 accuracy. Our model outperforms their model in accuracy rate with less feature set. The study in [20] applied both J48 and SVM for classifying emails using a feature set of 30 features and yielded an accuracy rate of 0.88, our approach outperforms this result using the same classification algorithm J48 with a classification accuracy of 0.89. The study in [21] achieved high rate of accuracy in classifying phishing emails, it used a group of classification algorithms including Random Forest, SVM and decision trees. However, this study was built on a small and not verified phishing data set. In our approach we are applied J48 Random forest and Random tree approach different attacks on networks Our model achieved 0.93 accuracy. Our model outperforms their model in accuracy rate with less feature set. 7. CONCLUSION Cybercriminals are continually finding new ways to avoid detection and develop techniques to and manipulate communications and improve the success rates of phishing attack. Phishing attacks combine technology and social engineering to gain access to restricted information. The most common phishing attacks today send mass email directing the victim to a web site of some perceived authority. This paper is focused on wireless network and phishing attacks. To analysis attacks on network signal we are applying different data mining algorithms like J48, random Forest and random Tree algorithms on network dataset of 3 years with 6 different attribute name “Company”, “Data Provider”, “Data Used”, “Date”, “Class”, & “Signal” from different telecom companies to achieve 95 to 99% accuracy with a false positive rate of 0.5-1.5% and modest false negatives. Thus, the comparative views shows that J48 algorithm for phishing detection achieves better performance as compared to random Forest and random Tree algorithm. REFERENCES [1] A Review on Phishin Attacks and Various Anti Phishing Techniques [2] Stajano, F. and Wilson, P. Understanding scam victims: Seven principles for systems security. Commun. ACM 54, 3 (Mar. 2011), 70–75.
[3] Jagatic, T.N., Johnson, N.A., Jakobsson, M., and Menczer, F. Social phishing. Commun. ACM 50, 10 (Oct. 2007), 94–100. [4] Hong, J. Why have there been so many security breaches recently? Blog@CACM. [5] CERT. Incident note IN-9903.http://www.cert.org/incident notes/IN-99-03.html, April 1999. [6] Ivan Arce. The shellcode generation. IEEE Security & Privacy, September/October 2004. [7] Ivan Arce. The rise of the gadgets. IEEE Security & Privacy, September/October 2003. [8] Engin Kirda and Christopher Kruegel 2005 ,” Protecting Users Against Phishing Attacks with AntiPhish” Computer Software and Applications Conference, COMPSAC 2005. 29th Annual International (Volume: 1 ). [9] Madhusudhanan Chandrasekaran Ramkumar Chinchani Shambhu Upadhyaya,” PHONEY: Mimicking User Response to Detect Phishing Attacks”, WOWMOM '06 Proceedings of the 2006 International Symposium on on World of Wireless, Mobile and Multimedia Networks, Pages668-672, IEEE Computer Society Washington. [10] Ying Pan, Xuhua Ding 2006”Anomaly BasedWeb Phishing Page Detection” Proceedings of the 22nd Annual Computer Security Applications Conference (ACSAC'06). [11] Craig M. McRae Rayford B.Vaughn2007 ,”Phighting the Phisher:Using Web Bugs and Honeytokens to Investigate the Source of Phishing Attack“, Proceedings of the 40th Annual Hawaii International Conference on System Sciences (HICSS'07). [12] Alireza Saberi, Mojtaba Vahidi, Behrouz Minaei Bidgoli 2007, “Learn To Detect Phishing Scams Using Learning and Ensemble Methods”, Proceedings of the 2007 IEEE/WIC/ACM. [13] Eric Medvet, Engin Kirda, Christopher Kruegel 2008,”Visual-Similarity-Based Phishing Detection” Proceedings of the 4th international conference on Security and privacy in communication networks. [14] Maher Aburrous, M. A. Hossain, Keshav Dahal, Fadi Thabatah 2009,”Modelling Intelligent Phishing Detection System for e-Banking using Fuzzy Data Mining” CyberWorlds, 2009. CW '09. [15] Divya James and Mintu Philip2012,”A NOVEL ANTI PHISHING FRAMEWORK BASED ON VISUAL CRYPTOGRAPHY” International Conference on Power, Signals, Controls and Computation (EPSCICON). [16] Mohd Mahmood Ali and Lakshmi Rajamani2012,”APD: ARM Deceptive Phishing Detector System Phishing Detection in Instant Messengers Using Data Mining Approach” Springer Berlin Heidelberg. [17] Isredza Rahmi A HAMID, Jemal ABAWAJY, Tai-hoon KIM2013,“Using Feature Selection and Classification Scheme for Automating Phishing Email Detection” Studies in Informatics and Control22(1):61-70·March 2013. [18] Moh'd Iqbal AL Ajlouni1, Wa'el Hadi,Jaber Alwedyan2013,”Detecting Phishing Websites Using
491
INTERNATIONAL JOURNAL OF INNOVATIVE TECHNOLOGY AND CREATIVE ENGINEERING (ISSN:2045-8711) VOL.8 NO.6 JUNE 2018
Associative Classification�European Journal of Business and Management www.iiste.org ISSN 2222-1905 (Paper) ISSN 2222-2839 (Online) Vol.5, No.23, 2013. [19] International Journal of Network Security & Its Applications (IJNSA) Vol.8, No.4, July 2016. [20] Phishing Activity Trends Report, http://docs.apwg.org/reports/apwg_trends_report_q1q3_2015.pdf, Accessed June 2016. [21] https://security.googleblog.com/2014/11/behind-enemylines-in-our-war-against.html , Accessed June 2016. [22] Network security vulnerabilities threats and attacks pdf. [23] Gaganjot kaur department of computer science and engineering GNDUAmritsa (pb.), India has introduced J48 Algorithm. [24] Random Forest Algorithm Explained by Wikipedia- The free Encyclopaedia. [25] Random Forest Tree Algorithm Explained by WikipediaThe free Encyclopaedia. [26] CAPEC-164: Mobile Phishing. https://capec.mitre.org/data/definitions/164.html [27] Ashford, W. (2014) Phishing Attacks Track Mobile Adoption, Research Shows. http://www.computerweekly.com/news/2240215873/Phis hing-attacks-track-mobile-adoption-research-shows. [28] Kessem, L. (2012) Rogue Mobile Apps, Phishing, Malware and Fraud.https://blogs.rsa.com/rogue-mobileapps-phishing-malware-and-fraud. [29] Klein, A. (2010) The Golden Hour of Phishing Attacks. http://www.trusteer.com/blog/golden-hour-phishingattacks. [30] European Journal of Business and Management www.iiste.org (Paper) ISSN 2222-2839 (Online) Vol.5, No.23, 2013. [31] https://www.ideacellular.com/. [32] https://www.tatadocomo.com/ [33] https://www.airtel.in/. [34] www.bsnl.co.in/ [35] https://www.jio.com/
492
INTERNATIONAL JOURNAL OF INNOVATIVE TECHNOLOGY AND CREATIVE ENGINEERING (ISSN:2045-8711) VOL.8 NO.6 JUNE 2018
Framework for Opinion Mining Approach to Augment Education System Performance Amritpal Kaur Department of Computer Science and Engineering, Thapar Institute of Engineering and Technology, (Deemed to be University, Patiala),India E-mail: akaur5_be15@thapar.edu Harkiran Kaur Department of Computer Science and Engineering, Thapar Institute of Engineering and Technology, (Deemed to be University, Patiala),India E-mail: harkiran.kaur@thapar.edu Abstract- The extensive expansion growth of social networking sites allows the people to share their views and experiences freely with their peers on internet. Due to this, huge amount of data is generated on everyday basis which can be used for the opinion mining to extract the views of people in a particular field. Opinion mining finds its applications in many areas such as Tourism, Politics, education and entertainment, etc. It has not been extensively implemented in area of education system. This paper discusses the malpractices in the present examination system. In the present scenario, Opinion mining is vastly used for decision making. The authors of this paper have designed a framework by applying Naïve Bayes approach to the education dataset. The various phases of Naïve Bayes approach include three steps: conversion of data into frequency table, making classes of dataset and apply the Naïve Bayes algorithm equation to calculate the probabilities of classes. Finally the highest probability class is the outcome of this prediction. These predictions are used to make improvements in the education system and help to provide better education. Keywords - Opinion Mining, Naïve Bayes, Examination System.
organization in the market, enhancing the quality of the particular product manufactured by these organization. Opinion mining modeling is done by three approaches – A. Machine Learning approach(ML):- Machine Learning approach (ML) is beneficial for classification of opinions whether it represents positive or a negative sentiment. This approach is categorized as: Supervised Machine Learning(SML) SML includes labeled dataset where opinions are labeled with appropriate names. Unsupervised Machine Learning (UML) UML includes unlabeled dataset in which opinions are not properly labeled with appropriate names. B. Lexicon Based approach: - Lexicon Based (LB) approach is based on finding the sentiment lexicon which is utilized for classifying the text. In this either dictionary or corpus based approach is applied by semantic methods. C. Hybrid approach:- Hybrid approach (HB) is the combination of Machine Learning and Lexicon Based approach. It has been proved that this combination gives better performance because it uses the Deep Learning and feature extraction method to increase the efficiency of model. Machine Learning
1. INTRODUCTION Micro blogging and social media sites have become most easy and common means of communication among peer users. In the recent years, it has been observed that social networking sites such Facebook, Twitter and other similar sites have made a huge impact on people’s life and activities. It is observed that people feel free to share their opinions on the internet. Billions of web clients are utilizing social sites to extract the opinions of people on various topics. The process of extracting the opinions of the people, analyze then and classify the sentiment behind these opinions is called Opinion Mining. Opinion Mining (OM) is the area of Natural Language Processing (NLP) and Artificial Intelligence (AI) for extracting the views about particular topic and classify it as positive, negative or neutral based on people’s emotions and sentiments [4]. This is used for decision making in various fields such as finding client satisfaction, reputation of the
AI
Data Mining
Deep Learning
Fig 1: Layered approach of Data Mining In many developing countries such as Fiji and Korea, Government uses sentiment analysis to improve the present education system. Government has taken many decisions in the education field for various parameters such as extracting the opinions of students regarding higher studies, what type of environment they want in educational institutes,
493
INTERNATIONAL JOURNAL OF INNOVATIVE TECHNOLOGY AND CREATIVE ENGINEERING (ISSN:2045-8711) VOL.8 NO.6 JUNE 2018
how teacher’s behavior and method of teaching affects the student’s curriculum and performance in academics with the help of this method. Due to this the Government uses Opinion mining as a key point in decision making for educational issues. This paper implements and represents the analysis of the opinion of the students about the examination malpractices among Secondary school students in India. These malpractices have a great impact on the student’s performance scale factor. In the proposed students can share their opinion freely on social media regarding this problem, discussing what are reasons to behind these activities, how these affect student’s performance. 2. RELATED WORK Gamal D., Et.al in[1] has proposed a technique which demonstrates the research work done on dataset of the social media and illustrates how to improve the efficiency of the models and get more accurate results. Firstly it explained the three approaches for sentiment classification: ML, LB and HB. In this paper various ML algorithms were applied with the different Feature extraction methods to improve efficiency of classification model. It is stated by the authors that Unigram with SVM is more accurate than other algorithms of ML. Feature extraction is important aspect in Sentiment Analysis. Many researchers integrate multiple methods with different features to see the effect on efficiency of the proposed model. Lavanya K. and Deisy C. [11] gave the idea to extract the data belonging to different domains. It is difficult to train a classifier model so that it can classify the tweets belonging to different domains. Twitter serves as platform for public to share their views about different kinds of products, politics, etc. One classifier performs excellent for one domain but poor for the other domain. Some researchers suggest the SVM to train the data set on feature sets. And SVM gives more accuracy for multi-class data. Data parsing is used to represent words in the form of negative and positive scores. The authors proposed A topic adaptive classifier which can be used to overcome this problem .This classifier uses two vectors- text feature and non text features. This features values are calculated as point wise mutual information and information retrieval. The non features are classified under temporal features, emoticon features and punctuation features. Napitu F. Et.al [10] stated that, it is very important for companies to maintain their customers in the competitive market. Researchers evaluated a term Churn Management which is used to maintain their valuable customer and predicting customer’s churn including complement data and customer usage. Two techniques were followed by the authors in their paper, to predict the model for churn rate as Opinion Finder and Google Profile. Opinion Finder represents customer’s opinions as positive and negative words. The technique of Google profile for mood analysis states this technique has 6 dimensions. These include Sure, Kind, vital and Happy., calm and alert. Predictive Model of churn rate requires two inputs a. the past 3 month tweets b. the same combined with frequent time series moods. A recurrent neural network is mostly used to predict the changes in the churn rate.
Adinarayana S.and Ilavarasan E.in [2] proposed an Algorithm – “Over Sampled Imbalance Data Learning(OSIDL)” to retrive the information from the imbalanced data sets and are compared with the data available on twitter corpus by using traditional C4.5 Algorithm. Imbalance dataset exist in the classes which are not balanced. This method is applied by dividing the dataset into majority and minority data-subsets. minority sub set is further processed as: i. First step of OSIDL was constructing improved minority data sets. Then, minority datasets are analyzed to remove the noisy instances to generate pure data set and resample it. After this, the newly minority data set and strong majority dataset were combined to form a single balanced dataset, which increases the accuracy of the algorithm. Also some experiments were conducted by authors to determine the effectiveness of the OSIDL Algorithm, by calculating the precision, recall, TP rate etc. Zhang Z., Li H. and Yu W. in [3] proposed a paper which explores the two main aspects, i.e. clustering and classification. Clustering analyzes the reviews of customer related to particular attributes such as price aspect and service attitudes. The authors proposed VC-word2vec Algorithm for the clustering. However the sentiment classification divided the customer’s sentiment as positive, negative and neutral sentiments. This algorithm used high dimensional words to overall semantics sentences, and then voting algorithm for clustering according to the features words. For conducting the sentiment classification the authors proposed an algorithm based on ED-TextRank, which focus on the selection of aspect features and combines sentiment dictionary with TextRank. This analysis is done for predicting the market value and future demand of the product After applying Various experiments are conducted with these algorithms , EDTextRank give more accuracy than others. Zhang T. in [5] studied some case studies and concluded that people used to watch TV program online and gave feedback for different TV programs. Subjective evaluations of TV programs are executed on the basis of satisfaction survey,that analyzes how much user is satisfied by the channels or programs. Objective and subjective evaluations are differentiated by 2-POS Subjective model which is dependent on dictionary (“Corpus”). Then it is evaluated by POS tagging, followed by judging sentiment words orientation. This was done by applying SO-PMI (Sentiment Orientated Point-wise mutual information). It is UML method that measures the relevance of words by computing occurrences of various words. Different experiments are performed to meet the criteria of above algorithms. Ejaz A., et.al in [6] compared LB approach with ngrams to three models of ML, that is, Random Forest (RF) with word vec Decision Tree, and Random Forest with ngram. These models are applied on Amazon’s product feedback dataset. A sentence having a fact is called objective sentence and sentence having an opinion is called subjective sentence. First of all, data set taken from Amazon’s website is pre-processed. In the pre-processing stop-word, punctuation are removed and stemming is done. Then, a model classifier
494
INTERNATIONAL JOURNAL OF INNOVATIVE TECHNOLOGY AND CREATIVE ENGINEERING (ISSN:2045-8711) VOL.8 NO.6 JUNE 2018
was applied on dataset.. Various experiments are done on different data set by applying these algorithms. Prameswari P., Surjandari I.,Laoh E. in [7] focus on Bali island which is a popular tourist place. It was needed to make continuous improvement by giving attention to various services. And this could be done by identifying the opinion of the tourists based on online reviews on various websites. To perform above tasks Recursive Neutral Tensor Network (RNTN) was used. As the outcome of this algorithm, various services were improved to attract the more tourists towards Bali Island. The dataset was taken from a trusted website. Then data cleaning and preprocessing was done, followed by applying this algorithm. Based on various experiments the results shown by RNTN were better than the other algorithms. Soni D., Sharma M., Khatri S. in [8] studied the opinions of people regarding political and non-political issues.it was observed that these issues are directly affected by views shared on social media. In this paper, a simple data set was taken from social sites during election time and opinions of user were analyzed. First of all data cleaning and preprocessed was done and then Logistic regression model was applied on data set and various parameters such as recall, precision rate were calculated to determine the accuracy of the above model. 3. COMPARATIVE ANALYSIS OF OPINION MINING APPROACHES Table I: Approaches of Opinion mining analysis S.No Approach Application Outcomes area 1. SVM model Social Media Accuracy of classifier[1] different ML models can be increased by using feature selection 2. Social Developed a OSIDL[2] Media(Twitter) new algorithm OSIDL to get the knowledge from imbalance datasets Proposed 3. VC-Word2vec Product algorithms Industry EDperforms more TextRank[3] accurate experiments than previous available methods Three steps were 4. SO-PMI[5] Social Media proposed: subjective and objective evaluations, to get feature words and opinions
Classified the sentiment of people about a particular Bali island by using RNTN algorithm. Customer Broadband Proposed a 6. Churn technique Churn Internet management, by Rate[10] using this technique companies can study customer’s sentiments. Analysis the 7. NaïveBayes[9] Education student’s opinion for education system by using Facebook data and results that NaïveBayes is better algorithms than other algorithms for educational data. But the idea to check upon examination malpractices is not discussed by government that how it affects the student’s life and what are the reasons for it. This paper includes the analysis of student’s opinion that what are the reasons for these malpractices and who is responsible for the same. 4. PROPOSED WORK The problem is malpractices present in examination centre of India. The malpractices include, cheating allowed, leakage of question paper before exams, Un-fair ways of checking answer sheets. This affects the result of hard working students. The analysis of reviews of students is discussed in this paper to overcome this problem. 5.
RNTN[7]
Data Collect ion
Tourism
Text Preproces sing
Feature Extract ion
Facebo ok
Normalizat ion
POS taggin g
Twitt er
Filteri ng Word Indexing
Classi fier Model
Naïve Bayes Neura l Netwo rk
Case Foldi ng
Stemm ing
Taxono my classific ation
Fig 2. Different phases of implementation 495
Data Visualiz ation
INTERNATIONAL JOURNAL OF INNOVATIVE TECHNOLOGY AND CREATIVE ENGINEERING (ISSN:2045-8711) VOL.8 NO.6 JUNE 2018
The proposed system of Opinion mining will be implemented by using the combination of tools Python and Natural Language Processing (NLP). Python has some in-built libraries but Natural Language Toolkit (NLTK) provides a platform to create python programs to interact with natural data and take decisions accordingly. In this section, a framework is provided which describes that how data is extracted from social sites, then preprocess the data and classify the opinions as positive, negative and neutral. [case study]This process has 5 following steps: A. Feedback collection: Students and Teacher’s review is taken by posting a questionnaire on social sites such as Facebook, Twitter. This questionnaire contains the basic questions such as: a) what are reasons for the malpractices in examination control board b) what are the effects of the same on student’s dedication towards the hard work. Twitter data was extracted using the Twitter Streaming API(web scraping). Keywords related to education such as curriculum reforms, education were used for keywords for streaming and retrieving the feedback from website. The feedback extracted from website can be kept in JSON format (JavaScript Object Notation) so that preprocessing steps can be implement on the educational dataset. B. Text Pre-processing: After extracting the data from the social sites it requires a series of pre-processing steps applied before the data is used for Text Mining. Text pre-processing contains the several steps which are applied according to needs of the case study. These steps which are used in this study of this dataset are normalization spellings, remove missing values, case folding, filtering, lemmatization and stemming. Table II describes these steps of text preprocessing: Table II : Steps of Text Pre-Processing S.No. Task Description 1. Spell checker The process of correcting misspelled words. 2. Stopword The process of removing Removal meaningless words, punctuations and ‘to’, ‘the’ are also removed by step 3. Case Folding make the whole document in one form. 4. Stemming The process of reducing the derived words into their stem (root word) e.g. the combination word has the root word combine. C. Aspect Extraction : Aspect Extraction is simply stated as reprocessing the data and take out the essential features from the data. This can be done by various steps such as removing all the words which do not begin with alphabetic order, it simply means that removing the words starting with Numbers or with Special characters. Next step is removing stop words such as is, am, are present in the text. After it various steps such as POS tagging, Word Indexing, Taxonomy Formulation are performed to extract feature. Table III describes the various stages:
496
Table III : Stages of Feature Extraction No. Stage Description 1 POS tagging It is the process to find nouns and determining the semantic of words present in text. 2 Noun Indexing The process of indexing nouns in the text. 3 Taxonomy It is the process of Formulation grouping the nouns into categories that are present in the dataset. D. Classifier Model:- This step includes two stages: Training and Classification. In training stage, the model is trained by using Naïve Bayes algorithm on some part of the dataset. In classification that trained model is used to predict the outcomes. Naive Bayes is used because it is observed in various experiments this algorithm gives more accurate results with the educational dataset. As this model gives more accuracy that‘s why it is normally used . Equation 1 shows the Naïve Bayes for opinion mining[12]: (1) Where s is a opinion. M is a comment. P(s) is the probability of a opinion. P(M|s) is the probability that a given comment is being classified as a opinion . P(M) is the probability that it is actually a comment. E. Analysis the results:-The basic purpose of the analysis is to get useful information from the feedback for better interpretation and understanding student’s emotions regarding educational system especially about malpractices in the Examination Control System. Government can use this analysis to give idea to check upon examination system so that they can take better decision for the students, and quality of education can be improved. To attain this purpose, various visualization tools such as charts, graphs can applied on the results of opinion mining. It will help the Government in decision making and save time of the communities. 7. CONCLUSION Opinion Mining has great potential in the field of education. It provides an analysis which is very helpful in decision making. This paper showcases Student’s feedback on malpractices in the examination system (source: Facebook, Twitter). In this paper, NaïveBayes Algorithm is suggested to analyze the opinions on malpractices in education system because this algorithm is well suited for the education dataset. The proposed technique is used to overcome with the un-fair means of conducting examinations. This will help the Government to get more ideas by analyzing the outcome of this technique and implement new rules and regulations for minimizing the malpractices in examination control system.
INTERNATIONAL JOURNAL OF INNOVATIVE TECHNOLOGY AND CREATIVE ENGINEERING (ISSN:2045-8711) VOL.8 NO.6 JUNE 2018
REFERENCES [1] A comparative study on opinion mining algorithms of social media statuses. Gamal, Donia, et al. 2017. cario : s.n., 2017 [2] An Efficient approach for Opinion Mining from Skewed Twitter corpus using Over Sampled Imbalance Data Learning. Adinarayana, Salina and Ilavarasan, E. 2017. india : s.n., 2017. [3] Fine-grained Opinion Mining : An Application of Online Review Analysis in the express indusy. Zhang, Zhibin, Li, Hong and Yu, Wendong. 2017. china : s.n., 2017. [4] https://searchbusinessanalytics.techtarget.com/definition/ opinion-mining-sentiment-mining. [Online] [5] Key Technologies of TV Programs Subjective Evaluations Based on Opinion Mining. Zhang, Taozheng. 2017. china : s.n., 2017. [6] Opinion Mining Approaches on Amazon Product Reviews: A Comparative Study. Ejaz, Afshan, et al. 2017. karachi : s.n., 2017. [7] Opinion Mining from Online Reviews in Bali tourist area. Prameswari, Puteri, Surjandari, Isti and Laoh, Enrico. 2017. indonesia : s.n., 2017. [8] Political Opinion Mining Using E-social Network Data. Soni, Deepak, Sharma, Mayank and Khatri, Sunil Kumar. 2017. noida : s.n., 2017. [9] Student opinion mining regarding educatoinal system using Facebook Group. Tanwari, NIsha, Jalbani, Akhtar Hussain and Channa, Muhammad Ibrahin. 2017. Nawanshah : s.n., 2017. [10] Twitter Opinion Mining Predicts Broadband Internet’s Customer Churn Rate. Napitu, Fiernad, et al. 2017. indonesia : s.n., 2017. [11] Twitter Sentiment Analysis Using Multi-Class SVM. Lavanya, K and Deisy, C. 2017. 2017. [12] Mining techniques on education reforms. Omar, Mwana Said, et al. 2017. china : IEEE, 2017
497
INTERNATIONAL JOURNAL OF INNOVATIVE TECHNOLOGY AND CREATIVE ENGINEERING (ISSN:2045-8711) VOL.8 NO.6 JUNE 2018
Emerging Prospects of e-Commerce through CRM practices in the modern Banking Industry John Paul .M Assistant Professor, Sathyabama University, Chennai, India. E-mail: mjohnpaul2011@gmail.com Chemmalar.A Assistant Professor, Jeppiaar Maamallan Engineering College, Chennai, India.
Abstract- e-Commerce is a emerging platform where
the business are brought into the next level in modern business industries like Manufacturing, Banking, Tourism ,Hospitality and other service providers in India. The upcoming business players are adopting multi dimensional approach to reach the path of success. The major challenges and task of all kind of business is to maintain the large customer forum to make the industry healthy. The CRM is a most popular method to strengthen the business and customer value to reach the point of success. This study is the attempt to bring the challenges, needs and importances of e-commerce by adopting appropriate applications and tools. We brought some recommendations and conclusion based on findings to shape the industry to meet the global antagonism. Keywords- e-banking, Business and Customer.
1. INTRODUCTION In the history of Indian banking system, the last decade has turned into the different direction towards technological advancement and modern application with the help of information technology which control the entire world and playing as a role of pioneer in any kind of industry to make the work is easy and flexible. Now a day’s all the industries mainly the industry of banking survives and reaching the path of success by adopting innovated technologies and software to compete others in its industry. Today’s Information technology has changed the business in the form of smart and fast accessible concern with excellence in their work . All the trends in IT sector are then discussed to see their relevance to the status of Indian banks. Banking sector always stand at the forefront of the economy and innovation has paramount concern to the application of modern technical devices. Electronic delivery channels, ATMs, variety of cards, web based banking, and mobile banking are the names of few outcomes of the process of automation and computerization in Indian banking sector. Technical inventions, automation and IP based network have amplified bank's productivity and efficiency manifold. This has further led to the move from brick banking to concept of
'click banking'. The present paper attempts to analyse the applications of IT in banking sector. 2. LITERATURE REVIEW CRM, marketing, sales, service and support and information technology and information systems. Articles falling outside these functional categories were categorized as general (2010). It was found that the most common category of CRM articles belonged to the IT & IS category, followed by the general category, the marketing, the sales and the service & support categories. There were, in relative terms, a substantial number of articles belonging to the general category (2012). 2.1 E-CRM IN BANKS The modern banks have been striving hard to offer the best of products to customers enabling them to enjoy the latest and hassle free banking Technology, people and customer are the three elements on which hinges the success of banking in the e-millennium. Technology will be an enabler in managing the pace and quantum of change. Success in technology can be brought about by skilled human resources. In response to these technological challenges, organizations have to evolve internal capabilities and skilled human resource management which is fundamental in generating these capabilities. However, ultimately the bank’s performance depends upon the satisfaction of its customers. 2.2 RESEARCH METHODOLOGY Research comprises defining and redefining problems, formulating hypothesis on suggested solution, collection, and at last carefully listing the conclusion to determine whether they fit the formatting hypothesis. This study has done to the customers of some regional rural banks such as pallavan Grama bank through structured questionnaire and the data source of primary and secondary like Different type report and records of those companies , journals, magazines and websites of respective banks. Before going to the full-fledged data collection with 120 respondents, the questionnaire was tested with 25 respondents to measure the reliability and the end of the reliability test found the Cronbach alpha values stood as 0.58. Duration of this study was 3 months in the field of business with the target customer of 120 out of the population those who regularly making a transaction with business (loyal customer) based on
498
INTERNATIONAL JOURNAL OF INNOVATIVE TECHNOLOGY AND CREATIVE ENGINEERING (ISSN:2045-8711) VOL.8 NO.6 JUNE 2018
convenience sampling method. Area of study which I done at Chennai city circle , in respect of covering upper class customer those who maintain the relationship in corporate companies. 2.3 CURRENT STATUS OF E-CRM IN INDIAN BANKS Internet have enabled banking at the click of the mouse. At present there are five functional categories for online banking sites – on line brochure center, interactive bank, e-mails, calculations and cyberbanks, which offer customers access to account information, inter-branch funds transfer and utility bill payments. Banks have tied up with service providers in telecom and power sectors like MTNL, BSES and cellular service providers for allowing their customers to make bill payments online. In India, new private sector banks like ICICI Bank, HDFC Bank, Global Trust Bank and UTI Bank, have taken the lead in e-banking. Among the foreign banks, Citibank, has noticeable presence, while others like Federal Bank, HSBC Bank, Deutsche Bank and ABN Ambro Bank, are moving towards becoming big players in ebanking. 2.4 THE USE OF E-BANKING IN KEEPING CRM All the business either modern or traditional, supposed to follow different ways of e-banking methodology to get the work from different type of people and team in CRM implementation, based on their capacity and economic status. Here, some of modern banks had followed these types of prominent role in the platform of CRM practices to build the better brand image and social status. S. Opinion No of Percentage No respondents Customer care 1 12 10 centers Customers 2 15 12.5 Forum s Service 3 18 15 Delivery Awareness 4 14 11.7 camp Feedback 5 11 9.2 session Team 6 17 14.2 meetings 7
Product launch
15
8
Crating loyalty
18
12.5
15 Table: 1.1 Source: Primary As per the above table, Creating loyalty and service delivery with the customer has opted by 15% out other 8 modules, follow up of Team meetings has occupied by 9.2%.Its finally end with feedback session14.2 % of the respondents.
2.5 E-CRM FUTURE PROSPECTS McKinsey survey reveals that the global market for IT-enabled services would be $140 billion by 2008, of which $17 billion could belongs to India. Out of this, India has about $450 millions e-CRM market. To take advantage of this growing market, global giants like PeopleSoft, SAP, Baan, Nortel, Talisma Corporation, Oracle Corp., Pivotal, and Siebel Systems are planning to invest in India so as to provide eCRM softwares and services to Indian companies including banks. This will facilitate the e-CRM in Indian banks. S. Importance of No of Percentage No communication respondents 1
Brand image
5
4.2
2
Social status
14
11.7
3
Quality of work life
15
12.5
4
Job satisfaction
16
13.3
5
Tool of motivation Mobilizing Team spirit
18
15.0
13
10.8
7
Updating technology
15
8
Maximizing CRM
24
6
12.5 20
Table: 2.1 Source : Primary As per the above table, Maximizing CRM has opted by 20% out of other 8 modules, follow up of Tool of motivation has occupied by 15%.Its finally end with Brand image 5% of the respondents. 4. THE SCOPE OF CRM FOR MASSIVE OPPORTUNITIES Entire business world is sustaining in the market and competing others by the way of their effective communication. Success is the motto of all kind of business in the modern world in the track of progress of their work. Now a day the e-banking style and pattern will determine growth and standard of business. In this regard we would like to find out how well the e-banking modes will make relationship status to create and update and bring back the lost customer from the market and mainly establishing the brand. 5. RESULTS AND DISCUSSIONS Based on the study, 55% of the respondents were highly aware and 25 % were aware about CRM activities of the company will mainly depends on its e-banking style and methods It will influence that success of business and as well as relationship management . 14% of the respondents were not highly aware about the process of e-banking activities to motivate others to reach the target on time .48% of the respondents were agree and only12 % were Strongly agree that the employee of modern business are giving proper respect to the customers and value their e-banking channel Only 10% of the respondents were agreed and only 5 % were strongly agreed that they are interested to provide feedback/ suggestions to the company. Majority (48%) of the respondents were strongly Disagreed with the same. It is noted from the analysis that maximum of the respondents are satisfied on the process of course module in different kind of communication.
499
INTERNATIONAL JOURNAL OF INNOVATIVE TECHNOLOGY AND CREATIVE ENGINEERING (ISSN:2045-8711) VOL.8 NO.6 JUNE 2018
7. CONCLUSION In the modern era of business has been modified to the global level to compete everybody in the progress of success. All the modern business are having additional focus and care to sustain in the top level for a long time by doing so many process and function through different kind of programmes and systems. The major capital of business has been considered as money earlier to win. Now they all realized that customer support and back up could be a very big capital in the modern world. So all the areas of business were turns into the operation towards maximizing relationship through effective e-banking system and channel in their business protocol. This study contributed toward understanding factors that might shape and influence success or failure of CRM technology implementation in different bank set-up. Implementation of our CRM initiative should enable you to see improvements in all of these areas. A Wellexecuted CRM program should result in increased employee satisfaction, renewed sales confidence and improved personal productivity. In future more no research can carry forward in the aspect of CRM outlets and e-banking barriers in the Relationship management. We could strongly declare that the e-banking is a tool of relationship management in regional rural banks and brings the scope for great opportunities in the platform of success. REFERENCES [1] Davids, M., 1999. How to avoid the 10 biggest mistakes in CRM. The Journal of Business Strategy, 20 (6), 22-26. [2] Davis, F. D., Bagozzi, R. P., Warshaw, P. R., 1989. User acceptance of computer technology: A comparison of two theoretical models. Management Science, 35 (8), 9821003. [3] Day, G. S., 1994. The capabilities of market-driven organizations. Journal of Marketing, 58 (4), 37-52. [4] Dishaw, M. T., Strong, D. M., 1999. Extending the technology acceptance model with task-technology fit constructs. Information & Management, 36 (1), 9-21. [5] Goodhue, D. L., Wixom, B. H., Watson, H. J., 2002. Realizing business benefits through CRM: Hitting the right target in the right way. MIS Quarterly Executive, 1 (2), 79-94. [6] Grรถnroos, C., 1995. Relationship marketing: The strategy continuum. Journal of the Academy of Marketing Science, 23 (4), 252-254. [7] IDC (2004) worldwide customer relationship management applications market expected to surpass $11 billion by 2008, according to IDC. IDC. Retrieved 3 August,2004,from http://www.idcresearch.com/getdoc.jsp?containerId=pr20 04_07_26_122025. [8] Karimi, J., Gupta, Y. P., Somers, T. M., 1996. The congruence between a firm's competitive strategy and information technology leader's rank and role. Journal of Management Information Systems, 13 (1), 63-88.
500
@IJITCE Publication