India's largest platform and marketplace for GCC & AI leaders and professionals

Sign in

India's largest platform and marketplace for GCC & AI leaders and professionals

3AI Digital Library

Minimizing Policy Attrition

3AI August 16, 2020

Leading Life Insurance Company In Japan

Problem Statement

  • A high attrition in the customer base due to competition and miss-selling (45% is overall lapse rate)
  • Expectation was to build an approach to retain policies and to set up an early warning system to identify a potential attrition cases to prevent further revenue leakage

Analytics Led Approach

  • Attrition trends in the data over the years were analyzed and an approach was designed to provide a solution to contain further revenue leakage
  • Predictive attrition model was built to predict the propensity of policies to attrite
  • Given are high level process steps which were followed :
    • Data Load Exploration
    • Model variable Creation
    • Analytical Model Development
    • Business rules

Business Impact

  • Raw data was mined, and a methodology was built for developing a predictive attrition model to provide a probability score to influence the decisions to follow the case by the customer.
  • Model output was segmented to optimize the approach to follow the case and provided insights to treat each policy based on the segmented matrix Re-evaluate;Retain;Grow;Protect– for example, Retain is the quadrant high value and high risky policy, retaining such policies will optimize the effort as well as cost
  • Primary users, retention team were provided with insights for customer retention..

Critical Success Factors

  • 20% of the in-force portfolio has been identified with 69% of the premium to be at risk of attrition (Approx. $ 1.3 BN premium at risk)
  • Formulated a growth strategy to retain existing customers as well as grow their business
  • Integrated attrition prediction with every customer touch point system through a web service

    3AI Trending Articles

  • Data Science/Machine Learning and Software Quality

    Featured Article: Author: Biju Kalleppilli, Director-Performance Engineering, SAP Labs India Endless possibilities of data science applications in Software quality are probably an underrated one. At various stages of product testing life cycle, huge amount of data is generated and remain unexplored., primarily because the top management often become happy by looking at the quality metrics […]

  • Saudi Arabia to get Google Cloud services: Saudi Aramco

    Saudi Arabia, under its Vision 2030 reform plans, has encouraged foreign investment particularly in the technology sector and courted Silicon Valley players. Saudi Aramco Development Co, a subsidiary of Aramco, has teamed up with Google Cloud to offer cloud services to customers in Saudi Arabia, Aramco said on Monday. Saudi Arabia, under its Vision 2030 […]

  • 2020 marked a “turning point” for Cybersecurity in Australia

    Australians are on high alert about the threat of cyber attacks following Prime Minister Scott Morrison’s warning in June that Australia was targeted by a sophisticated “state-based” cyber-attack. It was, according to the Australian Cyber Security Centre (ACSC), the most significant and coordinated cyber-targeting against Australian institutions to date. The Prime Minister said while such […]

  • The virtuous cycle of Digital Transformation, Improved CX and AI/ Analytics

    Featured Article: Author: Mahadevann Iyerr, Co-founder & CEO, MAAVRUS Today customers are inundated with a plethora of choices and so it is very easy for them to shop around across multiple products &  retailers. Also given the level of increasing clutter around communication and the proliferation of new products and service offerings, new customer acquisition […]