a machine-learning based approach for zoning urban area in bundling schemes context

Investigating downstream freight demand is a prerequisite to accomplishing the overall strategic planning for implementing bundlingbased transportation systems. machine learning has recently become widely applied in order to support decision-making in several logistic operational levels: travel/arrival time prediction, occupancy forecasting of logistic spaces, route optimization and so on. nevertheless, strategic decision-making often overlooks flow tendencies forecasting. targeting this gap, the present paper aims at proposing a zoning process based on time series forecasting of supply chain demand through clustering service requesters. the main goal is to ensure effective long-term logistics system design and implementation in urban areas. with a view to conducting the proposed sequential approach, we have selected a set of machine learning models that are believed to be robust according to the literature and the achieved accuracy benchmark. in this respect, we have performed extensive computational experiments based on real-life data to test the performance of the applied models. considering the computational results, a number of analytical insights are illustrated.