Amputation-imputation based generation of synthetic tabular data for ratemaking

2025-09-02

AI Summary

Actuarial pricing often faces challenges in acquiring high-quality real data due to high acquisition costs and stringent privacy constraints. To address this, this paper introduces Multiple Imputation by Chained Equations (MICE)—for the first time in insurance pricing—as a synthetic tabular data generation method tailored for rate-making, and comparatively evaluates it against VAE and CTGAN. Using Generalized Linear Models (GLMs) as downstream evaluators, experiments demonstrate that MICE significantly outperforms deep generative models in preserving marginal distributions, inter-variable dependencies, and consistency of model parameter estimates—while also offering greater simplicity and interpretability. Moreover, MICE-based synthetic data augmentation substantially improves claim frequency prediction performance. This work establishes a novel, regulatory-compliant, and computationally efficient paradigm for data substitution in actuarial practice.

Technology Category

• Natural Language Processing: Code Generation / Program Synthesis from Natural Language
• Machine Learning: Deep Generative Models & Autoencoders
• Search and Optimization: Sampling/Simulation-based Search

Application Category

• Economics, Online Markets and Human Computation: Trust and reliance of crowd workers and data experts on GenAI
• Web Mining and Content Analysis: Web data generation and simulation
• User Modeling, Personalization and Recommendation: Explainable and interpretable methods for personalization

Abstract

Actuarial ratemaking depends on high-quality data, yet access to such data is often limited by the cost of obtaining new data, privacy concerns, etc. In this paper, we explore synthetic-data generation as a potential solution to these issues. In addition to discussing generative methods previously studied in the actuarial literature, we introduce to the insurance community another approach based on Multiple Imputation by Chained Equations (MICE). We present a comparative study using an open-source dataset and evaluating MICE-based models against other generative models like Variational Autoencoders and Conditional Tabular Generative Adversarial Networks. We assess how well synthetic data preserves the original marginal distributions of variables as well as the multivariate relationships among covariates. We also investigate the consistency between Generalized Linear Models (GLMs) trained on synthetic data with GLMs trained on the original data. Furthermore, we assess the ease of use of each generative approach and study the impact of augmenting original data with synthetic data on the performance of GLMs for predicting claim counts. Our results highlight the potential of MICE-based methods in creating high-quality tabular data while being more user-friendly than the other methods.

Problem

• Generating synthetic tabular data for actuarial ratemaking purposes
• Evaluating synthetic data preservation of distributions and relationships
• Assessing GLM consistency between synthetic and original data

Innovation

• Uses MICE for synthetic tabular data generation
• Compares MICE with VAEs and CTGAN models
• Evaluates statistical fidelity through GLM consistency