A forecasting approach for truckload spot market pricing

Abstract

Logistics is an important sector considering the increasingly competitive nature of industry today. Large-scale companies and third-party logistics providers want the most economical and reliable forecasting mechanism for pricing the truckload spot market in the sphere of logistics and supply chains. This paper investigates the price forecasting of the truckload spot market, which is an important area for the determination of future value from the viewpoint of truckers by considering comprehensive variables. Two methodologies are used to determine truckers’ spot price in the freight transport process, which are the artificial neural network and quantile regression, and a price forecasting framework is created. The framework is applied to two approaches: a route-based model and a general model in which all routes are considered together. Real data are used to demonstrate the applicability and feasibility of the proposed method. In this scope forecast performances can be assessed, the best methodology and approach can be selected, and projections can be carried out.