Case Study Leveraging an insurance customer retrieval solution to reactivate lapsed accounts
Client: Leading insurance company Industry: Financial Services Business Impact: • Comprehensive analysis • Account restoration • Improved ROI
Business Challenge The client faced an immediate challenge of accessing lapsed insurance policies with a potential of repayment within a specific time bracket. By identifying these accounts, the company can focus on their reactivation, which will result in an additional flow of revenue. The client was witnessing revenue loss and hence wanted to reactivate the lapsed insurance policies. However, while doing this, they wanted to ensure that the strategy is resulting in minimum wastage of money and effort.
Solution Blueocean Market Intelligence customized the insurance customer retrieval solution to address this particular problem. The two policies namely, Traditional and ULIP, were in two states - Inforce and Lapsed. • As a first step, the lapsed policies, having the potential of repayment by invoking inforce (customers with a payment profile > three years) attributes on the defaulted policies, were accessed • A binary logistic regression was utilised on lapsed and inforce datasets and a KS cutoff was decided based on the model results after which confusion matrix was built consisting of all the four wells
www.blueoceanmi.com
• The error pertaining to two wells in the matrix told about the reinforcement of attributes of inforce on lapsed policies and vice-versa
Traditional Policies Result Predicted
Actual
Lapsed
Inforce
Lapsed
7171
2827
Inforce
235
1998
ULIP Policies Result Predicted Lapsed Actual
Inforce
Lapsed
14478
8435
Inforce
304
1410
Factors like premium to be paid, income of the policy holder, occupation and the total sum assured at the end of maturity were found to be greatly affecting the model results. The confusion matrix shows a pictorial representation of the hypothesis used, where in 2827 and 8435 policies can be possibly retained in traditional and ULIP plans respectively. The above table also gives us the percentage correctness of the model, 74.9% and 64.7% for Traditional and ULIP policies respectively.
Outcome Factors that affected the predictive model were identified as: • • •
Premium to be paid Income of the policy holder Occupation and the total sum assured at the end of maturity
The study suggested it is always good to approach the lapsed policies within a specified time bracket after which the policies may get permanently lapsed. Based on our analysis, approximately 11,000 policies have been targeted from a portfolio of 50,000 and 8,000 have been successfully repossessed.
© 2014 Blueocean Market Intelligence. All Rights Reserved.
About Blueocean Market Intelligence Blueocean Market Intelligence is a global analytics and insights provider that helps corporations realize a 360-degree view of their customers through data integration and a multi-disciplinary approach that enables sound, data-driven business decisions. Since we live in a highly dynamic and multidimensional world, we believe the most effective business decisions come from a synthesis of data streams and not from one-dimensional sources. Using our 360 Discovery approach, we ensure the comprehensive use of all available structured and unstructured data sources, enabling us to bring the best to bear against each engagement. Strong decision support is enabled through a combination of analytics, domain expertise, engineering and visualization skills brought together in harmony. Leading companies have benefited from our partnership with financial growth, 360 views of their markets and competition, and improved customer acquisition, satisfaction and retention. Seattle | Phoenix | Denver | Chicago Cincinnati | Bangalore | Dubai | London For more information or to request a consultation, please email info@blueoceanmi.com or visit us online at www.blueoceanmi.com.