Optimization of Actuarial Neural Networks with Response Surface Methodology

Autor:	Ariuntugs, Belguutei, Madurang, Kehelwala Dewage Gayan
Rok vydání:	2024
Předmět:	Quantitative Finance - Risk Management Computer Science - Machine Learning
Druh dokumentu:	Working Paper
Popis:	In the data-driven world of actuarial science, machine learning (ML) plays a crucial role in predictive modeling, enhancing risk assessment and pricing strategies. Neural networks, specifically combined actuarial neural networks (CANN), are vital for tasks such as mortality forecasting and pricing. However, optimizing hyperparameters (e.g., learning rates, layers) is essential for resource efficiency. This study utilizes a factorial design and response surface methodology (RSM) to optimize CANN performance. RSM effectively explores the hyperparameter space and captures potential curvature, outperforming traditional grid search. Our results show accurate performance predictions, identifying critical hyperparameters. By dropping statistically insignificant hyperparameters, we reduced runs from 288 to 188, with negligible loss in accuracy, achieving near-optimal out-of-sample Poisson deviance loss. Comment: This work was presented at the Actuarial Research Conference (ARC) 2024.Research abstract submitted and presented at ARC 2024. More details can be found at \url{https://sites.google.com/view/arc2024/home}
Databáze:	arXiv
Externí odkaz:	http://arxiv.org/abs/2410.12824 Zobrazit plný text záznamu View this record from Arxiv