Showing cs.LGShow all
2 papers · 1 filter
cs.LG2024
Zero-Inflated Tweedie Boosted Trees with CatBoost for Insurance Loss Analytics
Banghee So, Emiliano A. Valdez
In this paper, we explore advanced modifications to the Tweedie regression model in order to address its limitations in modeling aggregate claims for various types of insurance suc…
cs.LG2024
Enhanced Gradient Boosting for Zero-Inflated Insurance Claims and Comparative Analysis of CatBoost, XGBoost, and LightGBM
Banghee So
The property and casualty (P&C) insurance industry faces challenges in developing claim predictive models due to the highly right-skewed distribution of positive claims with excess…