Artificial Intelligence-Based Cost Reduction for Customer Retention Management in the Indian Life Insurance Industry

Customer retention, measured as percentage policies renewed every year (persistency ratio), is one of the most important metrics for any life insurer. Due to several factors, including complexity of life insurance products, gap in understanding the importance of policy renewals and lack of appropriate engagement with the customers, higher lapsation rates for life insurance policies have been observed globally, specifically in India. Typically for a life insurance company, policy renewal premiums drive close to 60–70% revenue and retaining customers for a period of more than 6–7 years is critical to business profitability. Customer retention operations primarily include engaging with customers through telephonic renewal calls or other mediums to pay renewal premiums on time. With close to 70% of total policies present in the premium renewal base, tracking, scheduling, execution of customer retentions calls and campaigns contribute to a major cost head for life insurers. In this paper, the authors present an advanced analytic solution to effectively manage customer retention costs and improve the overall persistency. The paper demonstrates the use of several machine learning and deep learning neural network-based models to classify the customers based on propensity of not paying renewal premiums on time. The study includes a comparative analysis of model performance with the deep learning neural network model showing the highest performance. The propensity scores were used to create a solution driving differentiated retention strategy, matching customer segment with appropriate renewal efforts to reduce customer retention cost and improve persistency.