A COMPARATIVE MATHEMATICAL FRAMEWORK FOR BINARY CLASSIFICATION OF ELECTRIC-VEHICLE RANGE ANXIETY
Keywords:
Binary classification, Logistic regression, Random forest, XGBoost, Threshold optimization, Range anxietyAbstract
Range anxiety has limited the spread of electric vehicles to some extent due to concerns about travel and charging. This paper uses 50,000 observations to explore how well people with range-anxiety scores above 5 can be identified and how nine predictors related to mobility, charging, cognition, experience and demographics affect the fitted boundary. Missing values are filled with medians; otherwise, the IQR rule is used for capping extreme values, and continuous variables are Z-standardised. Regularised logistic regression, random forest and XGBoost are compared via a stratified 70:30 split and five-fold cross-validation; probability thresholds are searched and 100 Bayesian trials are used if necessary. XGBoost has achieved the highest accuracy (85.47%), precision (88.61%) and F1-score (84.56%) on the independent test set. Random Forest has the largest AUC of 0.9006, and XGBoost is only slightly lower at 0.8995. Electric-vehicle knowledge, environmental awareness and technology affinity account for 97.28% of the XGBoost importance and 90.92% of the random-forest importance. The above results separate the performance at a selected threshold from ranking ability across thresholds and also show the effect of non-linear relationships and cases near the score cutoff.References
[1] Rainieri G, Buizza C, Ghilardi A. The psychological, human factors and socio-technical contribution: A systematic review towards range anxiety of battery electric vehicles' drivers. Transportation Research Part F: Traffic Psychology and Behaviour, 2023, 99: 52-70.
[2] White L V, Carrel A L, Shi W, et al. Why are charging stations associated with electric vehicle adoption? Untangling effects in three United States metropolitan areas. Energy Research & Social Science, 2022, 89: 102663.
[3] Jaiswal D, Kant R, Singh P K, et al. Investigating the role of electric vehicle knowledge in consumer adoption: Evidence from an emerging market. Benchmarking: An International Journal, 2021, 29(3): 1027-1045.
[4] Song Y, Hu X. Learning electric vehicle driver range anxiety with an initial state of charge-oriented gradient boosting approach. Journal of Intelligent Transportation Systems, 2023, 27(2): 238-256.
[5] Rosales-Tristancho A, Carazo A F, Brey R, et al. Meta-analysis of consumers' trade-offs between range and charging infrastructure for electric vehicles. Transportation Research Part D: Transport and Environment, 2024, 134: 104342.
[6] Kristoffersson I, Pyddoke R, Kristofersson F, et al. Access to charging infrastructure and the propensity to buy an electric car. Transportation Research Part D: Transport and Environment, 2025, 139: 104588.
[7] Pamidimukkala A, Kermanshachi S, Rosenberger J M, et al. Barriers and motivators to the adoption of electric vehicles: A global review. Green Energy and Intelligent Transportation, 2024, 3(2): 100153.
[8] Ma X, Xie R, Guo L, et al. Range anxiety of battery electric vehicles: Quantification and determinants using real-world data. Transportation Research Part D: Transport and Environment, 2025, 146: 104837.
[9] Bas J, Cirillo C, Cherchi E. Classification of potential electric vehicle purchasers: A machine learning approach. Technological Forecasting and Social Change, 2021, 168: 120759.
[10] Ovchinnikov A, Forestell D. From range anxiety to charge anxiety: Operations scholars' reflections on the state of electric vehicles' public charging infrastructure. Service Science, 2026, 18(1): 55-78.