Use Cases

The working groups of the Actuarial Data Science committee are developing various use cases, which are presented below.

Update: Claim Frequency Modeling in Insurance Pricing using GLM, Deep Learning, and Gradient Boosting

Actuarial Data Science Committee in collaboration with the Non-Life Insurance Committee's Pricing Methodology Working Group, 03/2024.

What added value can machine learning methods offer for insurance pricing? To answer this question, we model claim frequencies using a large French auto liability insurance dataset and then compare the forecast results. In addition to the methods used in the first version of this case study—generalized linear models (GLM), deep neural networks, and decision tree-based model ensembles (eXtreme Gradient Boosting, "XGBoost")—we have included regularized generalized linear models (LASSO and Ridge), generalized additive models (GAM), and two other modern representatives from the class of decision tree-based model ensembles ("LightGBM" and "CatBoost").

Further informationther i

Forecasting Rare Events: Credit Scoring

Actuarial Data Science Committee, February 6, 2024.

The main question of this project is: Can machine learning techniques predict whether a customer will churn, file a claim, or repay a loan? And are these methods more accurate in their predictions compared to traditional statistical techniques like logistic regression? This use case explores these questions within the framework of binary classification, comparing the forecasting performance of various machine learning methods (including CatBoost, logistic regression with and without regularization, neural networks, LightGBM, and XGBoost). The analysis also explores topics like data preprocessing, model interpretability, overfitting and underfitting, and hyperparameter tuning. The goal is to provide an introductory guide to the application of actuarial data science methods on a supervised learning problem.

Further informationther i

Neural Networks Meet Mortality Prediction

Working Group *Statistical Methods* of the Actuarial Data Science Committee, 15.09.2020

What added value can neural networks provide for predicting life expectancy in multiple populations? To address this question, we first build a database with mortality rates for Japan, USA, Germany and six other European countries. In further steps, a classical mortality model is computed for each of these populations and the deep artificial neural network presented in Richman and Wüthrich (2018) is trained across populations.

Using these models, mortality predictions for different time periods are generated and compared. It is shown that for the majority of the populations studied, this cross-population neural network has a better forecasting ability compared to a "plain vanilla" Lee-Carter model.

Use (this Solvency II) case! Neural Networks Meet Least Squares Monte Carlo

Working Group *Statistical Methods* of the Actuarial Data Science Committee, 09/15/2020

The topic of artificial intelligence is on everyone's lips right now and the application areas are becoming more and more popular. In this case study, we want to address the risk capital determination of insurance companies in the Solvency II context and we will challenge the classical Least Squares Monte Carlo approach with neural networks. The realistic projection data generated specifically for this purpose from three life insurance and health insurance portfolios prepared in the context of this use case form the central component of this use case.