Interpretable Machine Learning Models for Predicting and Explaining Vehicle Fuel Consumption Anomalies

TL;DR

This paper presents an interpretable machine learning approach combining anomaly detection, domain knowledge, and explanations to identify causes of fuel consumption anomalies and provide actionable recommendations, achieving up to 35% fuel savings.

Contribution

It introduces a novel framework integrating unsupervised anomaly detection with interpretable models and domain insights for explaining fuel consumption anomalies in vehicle fleets.

Findings

Achieves up to 35% potential fuel reduction.

Provides explanations aligned with domain knowledge.

Demonstrates effectiveness on real-world telematics data.

Abstract

Identifying anomalies in the fuel consumption of the vehicles of a fleet is a crucial aspect for optimizing consumption and reduce costs. However, this information alone is insufficient, since fleet operators need to know the causes behind anomalous fuel consumption. 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 fleets. We measure the proposal regarding model performance, and using Explainable AI metrics that compare the explanations in terms of representativeness, fidelity, stability, contrastiveness and consistency with apriori beliefs. The potential fuel reductions that can be achieved is round 35%.