Adjusting Manual Rates to Own Experience: Comparing the Credibility Approach to Machine Learning

Credibility theory is the usual framework in actuarial science when it comes to reinforcing individual experience by transfering rates estimated from collective information. Based on the paradigm of transfer learning, this article presents the idea that a machine learning (ML) model pre-trained using a rich market data porfolio can improve the prediction of rates for an individual insurance portfolio. This framework consists first in training several ML models on a market portfolio of insurance data. Pre-trained models provide valuable information on relations between features and predicted rates. Furthermore, features shared with the company dataset are used to predict rates better than the same ML models trained on the insurer's dataset alone. Our approach is illustrated with classical ML models on an anonymized dataset including both market data and data from an European non-life insurance company, and is compared with a hierarchical Bühlmann-Straub credibility model. We observe the transfert learning stragegy combining company data with external market data significantly improves the prediction accuracy compared to a ML model only trained on the insurer's data and provides competitive results compared to hierarchical credibility models.