Truck Fuel Consumption Prediction Using Logistic Regression and Artificial Neural Networks

1. Introduction

The invasion of Ukraine by Russia has had a negative ripple effect in the global oil market. Russia has been one of the world’s largest oil producing country and now the war combined with economic sanctions on Russia, has had huge repercussions on the global economy as Ukraine and Russia are major players in the food, energy and mining sectors. Since Zimbabwe does not mine petroleum, it is a net importer and as such a price taker of the foregoing global oil prices, thus the efficient management of fuel by logistics companies has become a significant concern. One way of managing this is by analyzing the fuel consumption of trucks so as to better utilize the costly resource. The freight industry in Southern Africa is largely dominated by road transport and there are many cross-border transporters with both domestic and international origins. Transportation networks have become the major lifeline of modern societies, not only by ensuring individual well-being, but by also fostering economic growth through fast and reliable transportation activities, Muriel-Villegas et al. (2019) Since freight trucks carry the majority of commodities by road, they often consume much more fuel than other kinds of vehicles because of their characteristics such as large loads and long distance travel. Zimbabwe does not mine petroleum, thus it is a net importer of fuel and as such a price taker of the ongoing global oil prices. Since Russia invaded Ukraine there has been a turbulence in the global petroleum market which has been causing global spikes in crude oil prices. To add on this, Zimbabwe has had the highest regional fuel prices thus there is need for management to address the increasing cost of operation rising from both high fuel consumption and high fuel cost. Moreover, to reduce emissions thus lowering the carbon footprint, as the sustainable growth of the environment and energy has become a requirement all over the world, particularly in the transportation sector.