# An Enhanced Focal Loss Function to Mitigate Class Imbalance in Auto Insurance Fraud Detection with Explainable AI

arXiv: https://arxiv.org/abs/2508.02283 · HTML: https://mlsanity.com/paper/2508.02283/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 9 of its 34 references that are in the map.
- First posted on arXiv 4 Aug 2025.

## Builds on (most cited first, 9 of 9)

- [Learning Imbalanced Datasets with Label-Distribution-Aware Margin Loss](https://mlsanity.com/paper/1906.07413/) (2019)
- [Calibrating Deep Neural Networks using Focal Loss](https://mlsanity.com/paper/2002.09437/) (2020)
- [CurricularFace: Adaptive Curriculum Learning Loss for Deep Face Recognition](https://mlsanity.com/paper/2004.00288/) (2020)
- [WeightedSHAP: analyzing and improving Shapley based feature attributions](https://mlsanity.com/paper/2209.13429/) (2022)
- [AdaFocal: Calibration-aware Adaptive Focal Loss](https://mlsanity.com/paper/2211.11838/) (2022)
- [RKHS-SHAP: Shapley Values for Kernel Methods](https://mlsanity.com/paper/2110.09167/) (2021)
- [CHG Shapley: Efficient Data Valuation and Selection towards Trustworthy Machine Learning](https://mlsanity.com/paper/2406.11730/) (2024)
- [FW-Shapley: Real-time Estimation of Weighted Shapley Values](https://mlsanity.com/paper/2503.06602/) (2025)
- [A Convex Surrogate Operator for General Non-Modular Loss Functions](https://mlsanity.com/paper/1604.03373/) (2016)

## Abstract (arXiv)

Detecting fraudulent auto-insurance claims remains a challenging classification problem, largely due to the extreme imbalance between legitimate and fraudulent cases. Standard learning algorithms tend to overfit to the majority class, resulting in poor detection of economically significant minority events. This paper proposes a structured three-stage training framework that integrates a convex surrogate of focal loss for stable initialization, a controlled non-convex intermediate loss to improve feature discrimination, and the standard focal loss to refine minority-class sensitivity. We derive conditions under which the surrogate retains convexity in the prediction space and show how this facilitates more reliable optimization when combined with deep sequential models. Using a proprietary auto-insurance dataset, the proposed method improves minority-class F1-scores and AUC relative to conventional focal-loss training and resampling baselines. The approach also provides interpretable feature-attribution patterns through SHAP analysis, offering transparency for actuarial and fraud-analytics applications.