Interpretable machine learning models for predicting and explaining vehicle fuel consumption anomalies
Alberto Barbado, Óscar Corcho
Abstract
Identifying anomalies in the fuel consumption of vehicle fleets is crucial for optimizing consumption and reducing costs. However, this information alone is insufficient since fleet operators need to know the causes behind anomalous fuel consumption. Therefore, we combine unsupervised anomaly detection techniques, domain knowledge and interpretable Machine Learning models for explaining potential causes of abnormal fuel consumption in terms of feature relevance. The explanations are used for generating recommendations about fuel optimization that are adjusted according to two different user profiles: fleet managers and fleet operators. Results are evaluated over real-world data from telematics devices connected to diesel and petrol vehicles from different types of industrial vehicle fleets. We carry out an evaluation through model performance and Explainable AI metrics that compare the explanations in terms of representativeness, fidelity, stability, contrastiveness and consistency with prior beliefs.