Including individual customer lifetime value and competing risks in tree-based lapse management strategies

Abstract

A retention strategy based on an enlightened lapse model is a powerful profitability lever for a life insurer. Some machine learning models are excellent at predicting lapse, but from the insurer's perspective, predicting which policyholder is likely to lapse is not enough to design a retention strategy. In our paper, we define a lapse management framework with an appropriate validation metric based on Customer Lifetime Value and profitability. We include the risk of death in the study through competing risks considerations in parametric and tree-based models and show that further individualization of the existing approaches leads to increased performance. We show that survival tree-based models outperform parametric approaches and that the actuarial literature can significantly benefit from them. Then, we compare, on real data, how this framework leads to increased predicted gains for a life insurer and discuss the benefits of our model in terms of commercial and strategic decision-making.

Time-penalized trees (TpT): a new tree-based data mining algorithm for time-varying covariates

“…This is thus a time-dependent classification problem, where the target variable is the final outcome of the policies, the tree grows with the survival time and splits on potentially time-varying covariates such as age, rate, Customer Lifetime Value (CLV), face amount (FA) or gender. More detailed descriptions of the dataset used can be found in Valla et al and in Valla's works [43,42] 4.1 Properties of TpT for the maximal tree…”