Paper: arXiv 2410.12824

Authors: Belguutei Ariuntugs, Kehelwala Dewage Gayan Madurang

Abstract

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.

Complexity vs Empirical Score

  • Math Complexity: 5.5/10
  • Empirical Rigor: 5.0/10
  • Quadrant: Holy Grail — high math complexity, high empirical rigor

Why this score: The paper presents a solid application of classical Response Surface Methodology (RSM) and Central Composite Design (CCD) to hyperparameter tuning for Combined Actuarial Neural Networks (CANN). While the underlying statistical methodology (DOE/RSM) is well-established, its systematic adaptation to reduce computational costs in actuarial neural network tuning offers practical value and moderate mathematical rigor.

Research Flowchart

  flowchart TD
    A[Goal: Optimize Actuarial Neural Network Hyperparameters efficiently] --> B[Input: Actuarial Data & CANN Architecture]
    B --> C[Method: Factorial Design & Response Surface Methodology]
    C --> D[Process: Screen & Drop Insignificant Hyperparameters]
    D --> E[Outcome: Reduced Runs from 288 to 188]
    E --> F[Result: Near-Optimal Out-of-Sample Poisson Deviance]