A Sustainable Performance Assessment System for Road Freight Transport Based on Artificial Neural Networks

Abstract

The objective of this paper is to present a new multidimensional performance measurement model calculating the overall sustainable performance value applied to the road freight transport sector. The measurement system presented considers five main dimensions including economic, social, environmental, operational and stakeholder. This paper justifies the choice of these dimensions and details the calculation approach through the presentation of the different minimum conditions algorithms leading to the final global performance value. The model is then generalized here by means of the artificial neural network (ANN) which is found to be the most relevant modeling technique used in a variety of scientific domains. In this study, ANN is used to predict the value of the global multidimensional performance in road freight transport estimated following the machine learning of the program on a labeled database. The data on which the program trained emerged from our multidimensional performance measurement model. A model mainly designed for the sole purpose of quantifying the sustainable performance of a supply chain. To this end, we have identified five main dimensions recurrently cited in the literature, namely: economic, environmental, social, operational, and stakeholders. The dimensions' respective performances are obtained by employing a minimum condition algorithm, which returns the global multidimensional performance. The suggested model is general and may be applied to different disciplines.