Insurance claim level estimation and influencing factor analysis for electric vehicles: A case study in Changsha city

Objectives Claim amount levels reflect severity risk and facilitates risk estimation in insurance practice. This study supports risk management in electric-vehicle traffic insurance by establishing an effective classification framework for claim levels. Methods The Synthetic Minority Over-Sampling Technique (SMOTE) is applied to balance the distribution of claim amount levels in traffic insurance. This study applies six distinct models-Decision Tree, Random Forest, CatBoost, Support Vector Machine (SVM), Multila…

By the Truvace deskSeptember 16, 20261 min read1 sourcePeer-reviewedTRV-2026-1106· cite & verify

Insurance claim level estimation and influencing factor analysis for electric vehicles: A case study in Changsha city — "Motorway traffic - geograph.org.uk - 2980934" by James Allan is licensed under CC BY-SA 2.0. To view a copy of this license, visit https://creativecommons.org/licenses/by-sa/2.0/.

In brief

A peer-reviewed study in Traffic Injury Prevention collected electric-vehicle traffic insurance claims from Changsha, China, applied SMOTE for class balancing, and tested six machine learning models to classify Claim Amount Level, using SHAP to explain feature influence.

The work matters because accurate claim severity classification directly affects insurer risk pricing and reserve management for the growing EV fleet, but the source does not report deployment outcomes, external validation beyond Changsha, or impacts on premiums or claim handling.

Main points

Study used claim data collected from electric vehicles in Changsha, China and applied SMOTE to balance claim amount level distribution.
Six models were tested: Decision Tree, Random Forest, CatBoost, SVM, MLP, and LGBM, with Random Forest selected as optimal classifier.
SHAP analysis identified top predictors as Injury Claim Flag, Claim Type, and Claim Count During Policy, with driver faults interacting with injury status to elevate high claim probability.

The gain

Machine learning classification improves risk differentiation for electric-vehicle traffic insurance by predicting claim amount levels from policy and behavioral features.

The rundown

Researchers balanced imbalanced claim amount levels using SMOTE and compared six classifiers on EV insurance data from Changsha, evaluating classification performance, class separability, and business interpretability.

SHAP-based global and local explanations showed heterogeneous effects, where driver behavioral faults like negligence and insufficient safety distance interact with injury status to increase predicted probability of high claim levels.