India's largest platform and marketplace for GCCs & AI

Sign in

India's largest platform and marketplace for GCCs & AI
Become a Thought Leader
Become a 3AI Member

Sign in

3AI Digital Library

< Go Back

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

  • Rethinking Reasoning in AI with Multimodal Chain-of-Thought Prompting

    Featured Article by Rahul Pandey, Data Science & Applied AI Practice Leader, C5i Beyond Understanding to Reasoning As AI systems evolve, the true benchmark is no longer their ability to comprehend it, it’s their ability to reason. Today, we stand at the edge of a significant breakthrough: Multimodal Chain-of-Thought Prompting (MCoT), a technique that allows […]

  • Google investigates ethical AI team member over sensitive data handling

    Google’s diversity efforts have been questioned by employees and adds to years of angst, including several resignations and firings in the AI department. Alphabet Inc’s Google is investigating a member of its ethical AI team and has locked the corporate account linked to that person after finding that thousands of files were retrieved from its […]

  • Application of Reinforcement Learning in Supply Chain

    Author: Anindya Bera, Senior Manager – Anaytics, Genpact A supply chain is a complex network of individuals and agents who exchange materials or information in a business ecosystem. The items which are used on day-to-day basis are created by a global collaboration between suppliers, manufacturers, and logistics carriers. What makes this complex? It is the […]

  • Major Cybersecurity Incidents of 2020

    From ransomware schemes to supply chain attacks, this year melded classic hacks with extraordinary circumstances. WHAT A WAY to kick off a new decade. 2020 showcased all of the digital risks and cybersecurity woes you’ve come to expect in the modern era, but this year was unique in the ways Covid-19 radically and tragically transformed life around the […]