🤖 AI Summary
Non-life insurance pricing models suffer performance degradation in dynamic environments due to concept drift, yet systematic approaches for its detection and monitoring remain underexplored.
Method: This paper proposes a statistically grounded monitoring framework based on the Gini coefficient. Theoretically, we derive the asymptotic distribution of the Gini coefficient and establish a rigorous hypothesis testing procedure to distinguish spurious drift from genuine concept drift, clarifying their respective impact boundaries. Practically, we integrate the Gini index with deviation loss to formulate an operational monitoring workflow that informs model retraining decisions.
Results: Evaluated on real-world datasets with controlled concept drift injection, the framework accurately pinpoints performance degradation onset points, significantly enhancing both the stability and predictive accuracy of non-life insurance pricing models.
📝 Abstract
In a dynamic landscape where portfolios and environments evolve, maintaining the accuracy of pricing models is critical. To the best of our knowledge, this is the first study to systematically examine concept drift in non-life insurance pricing. We (i) provide an overview of the relevant literature and commonly used methodologies, clarify the distinction between virtual drift and concept drift, and explain their implications for long-run model performance; (ii) review and formalize common performance measures, including the Gini index and deviance loss, and articulate their interpretation; (iii) derive the asymptotic distribution of the Gini index, enabling valid inference and hypothesis testing; and (iv) present a standardized monitoring procedure that indicates when refitting is warranted. We illustrate the framework using a modified real-world portfolio with induced concept drift and discuss practical considerations and pitfalls.