case in point blueoceanmi.com | 1 Title: Incenvize exisng policies for a leading insurance company Industry: BFSI Country: India Challenge • A leading Insurance company was required to access the lapsed insurance policies having a potenal of repayment (and hence reacvaon), within a specific me bracket • Idenfy in which criteria can the exisng in-force policies can be incenvized • Variety of datasets pertaining to different types of policies had to obtained and processed thereaſter Approach • The two policies Tradional and ULIP were in two states - Inforce & Lapsed • Data cleaning was done using a proprietary machine learning tool • A binary logisc regression was applied on each of the policies with lapsed and inforce data Result • Factors that effected the predicve model were • Premium to be paid • Income of the policy holder • Occupaon and the total sum assured at the end of maturity • It was derived that it was always good to approach the lapsed policies within a specified me bracket aſter which the policies may get permanently lapsed FPO
2
Embed
Incentivize existing policies for a leading insurance company
From the lapsed insurance policies, identified ones that potential of repayment and used predictive models to device approach on preventing permanent lapse.
This document is posted to help you gain knowledge. Please leave a comment to let me know what you think about it! Share it to your friends and learn new things together.
Transcript
case in point
blueoceanmi.com | 1
Title: Incentivize existing policies for a leading insurance companyIndustry: BFSICountry: India
Challenge• A leading Insurance company was required to access the lapsed insurance policies having a potential of repayment
(and hence reactivation), within a specific time bracket • Identify in which criteria can the existing in-force policies can be incentivized • Variety of datasets pertaining to different types of policies had to obtained and processed thereafter
Approach• The two policies Traditional and ULIP were in two states - Inforce & Lapsed• Data cleaning was done using a proprietary machine learning tool • A binary logistic regression was applied on each of the policies with lapsed and inforce data
Result• Factors that effected the predictive model were • Premium to be paid • Income of the policy holder • Occupation and the total sum assured at the end of maturity• It was derived that it was always good to approach the lapsed policies within a specified time bracket after which the
About blueoceanblueocean market intelligence is a next-generation services organization with a deep focus on analytics, market intelligence and social intelligence, all uniquely delivered under one roof by 750+ plus professionals with deep domain expertise.
Our blended offshore/onshore delivery model, coupled with our vast experience in scalable delivery, enables us to deliver richer, more actionable insights very cost-effectively and with the speed and quality that today's business climate demands. In addition, our 360 Discovery™ process insures the comprehensive utilization of all available structured and unstructured data sources, enabling us to bring the best to bear against each and every project that we execute.