Transportation Market Rate Forecast Using Signature Transform

Gu, Haotian, Jacobs, Tim, Kaminsky, Philip, Guo, Xin, Li, Xinyu

arXiv.org Artificial Intelligence 

Linehaul transportation costs make up a significant portion of overall Amazon transportation costs. To manage these costs, Amazon has developed a variety of tools to manage linehaul capacity mix and procurement. One key input to all of these models is the forecast of transportation marketplace rates, which however are notoriously difficult to forecast - they are driven a number of factors: the ever-changing network of tens of thousands of drivers, shippers of all sizes with a mix of occasional, seasonal, and regular demand, a huge set of brokers, traditional and digital exchanges, and local, regional, national, and international economic factors of all kinds. In addition, the transportation marketplace frequently goes through fundamental shifts - whether because of wars, pandemics, fuel prices, or due to shifting international trade patterns. Although Amazon has purchased externally-created forecasts for some time, these forecasts are neither explainable nor sufficient/accurate to the specific Amazon needs. To address this challenge, we built a forecasting model based on time series data to predict weekly marketplace rates for the North America market, at both the national and the regional levels. Our approach incorporates an innovative statistical technique capable of efficiently capturing significant fluctuations in transportation marketplace rates.