Non-Heuristic Selection via Hybrid Regularized and Machine Learning Models for Insurance

2025-06-05

AI Summary

To address the dual challenge of enhancing both interpretability and predictive accuracy in customer purchase behavior prediction for travel insurance, this paper proposes a tightly coupled hybrid modeling paradigm—Lasso-CatBoost. First, Lasso regression performs interpretability-driven feature selection, yielding sparse linear coefficients that preserve statistical transparency and directional insights. Subsequently, the selected features are fed into CatBoost to construct a high-accuracy classifier. This approach overcomes the trust deficit of conventional black-box models in insurance risk management by jointly optimizing statistical interpretability and classification performance. Experimental results demonstrate that the hybrid model achieves an AUC of 0.861 and an F1-score of 0.808—significantly outperforming individual models (e.g., XGBoost, LightGBM, Random Forest) and pure regularization methods. Moreover, it reduces feature dimensionality by over 60% while retaining key business-relevant variables and their interpretable sign-based effects.

Technology Category

• Machine Learning: Transparent, Interpretable, Explainable ML
• Natural Language Processing: Interpretability, Analysis, and Evaluation of NLP Models
• Computer Vision: Interpretability, Explainability, and Transparency

Application Category

• User Modeling, Personalization and Recommendation: Explainable and interpretable methods for personalization
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking

Abstract

In this study, machine learning models were tested to predict whether or not a customer of an insurance company would purchase a travel insurance product. For this purpose, secondary data provided by an open-source website that compiles databases from statistical modeling competitions were used. The dataset used presents approximately 2,700 records from an unidentified company in the tourism insurance sector. Initially, the feature engineering stage was carried out, which were selected through regularized models: Ridge, Lasso and Elastic-Net. In this phase, gains were observed not only in relation to dimensionality, but also in the maintenance of interpretative capacity, through the coefficients obtained. After this process, five classification models were evaluated (Random Forests, XGBoost, H2O GBM, LightGBM and CatBoost) separately and in a hybrid way with the previous regularized models, all these stages using the k-fold stratified cross-validation technique. The evaluations were conducted by traditional metrics, including AUC, precision, recall and F1 score. A very competitive hybrid model was obtained using CatBoost combined with Lasso feature selection, achieving an AUC of 0.861 and an F1 score of 0.808. These findings motivate us to present the effectiveness of using hybrid models as a way to obtain high predictive power and maintain the interpretability of the estimation process

Problem

• Predicting travel insurance purchases using machine learning
• Combining regularized and hybrid models for better accuracy
• Maintaining interpretability while improving predictive performance

Innovation

• Hybrid regularized and machine learning models
• Feature selection via Ridge, Lasso, Elastic-Net
• CatBoost combined with Lasso for high AUC