Understanding Factors Affecting Fuel Consumption of Vehicles Through Explainable AI: A Use Case With Explainable Boosting Machines

A significant economic cost for many companies that operate with fleets of vehicles is related to their fuel consumption. This consumption can be reduced by acting over some aspects, such as the driving behaviour style of vehicle drivers. Improving driving behaviour (and other features) can save fuel on a fleet of vehicles without needing to change other aspects, such as the planned routes or stops. This is important not only for mitigating economic costs within a company, but also for reducing the emissions associated to fuel consumption, mainly when the vehicles have petrol or diesel engines. In this paper we show how Explainable Artificial Intelligence (XAI) can be useful for quantifying the impact that different feature groups have on the fuel consumption of a particular fleet. For that, we use Explainable Boosting Machines (EBM) that are trained over different features (up to 70) in order to first model the relationship between them and the fuel consumption, and then explain it. With it, we compare the explanations provided by the EBM with general references from the literature that estimate the potential impact that those features may have on the fuel consumption, in order to validate this approach. We work with several real-world industry datasets that represent different types of fleets, from ones that have passenger cars to others that include heavy-duty vehicles such as trucks.