The trucking industry is essential to companies and trade in the United States. Trucks are responsible for transporting nearly 70% of all goods moving throughout the country. An $800 billion industry, trucking has tentacles connecting actors throughout the supply chain. Trucking costs are impacted by many unpredictable factors resulting in market rates that are constantly fluctuating and causing regular disruptions to planned budgets and business operations.
Shippers regularly establish contracts with carriers to reduce their exposure to the volatility of the trucking market. However, the trucking industry is unique in the sense that contracts are often non-binding. Hence, carriers may forgo the terms of a contract if they deem it advantageous to sell their assets to the open market. As carriers sell their capacity to the highest bidder, shippers are forced to source their transportation needs elsewhere, often at a substantially higher cost.
When the trucking market spot rate increases, more contracted loads get rejected and shippers’ tender acceptance rates (TAR) with their carriers decrease. Carrier rejections can result in up to 35% higher transportation rates. The volatility of the spot rate causes a chain reaction impacting shippers’ business operations. The higher costs stemming from the spot rate increases are accompanied by lower customer service levels as well as disturbances to planned budgets and business operations.
To address this ripple effect, we developed a forecasting model to give greater visibility into the future of the spot rate and a Tactical Playbook to help safely navigate market volatility.
The forecasting model we developed accurately predicts the market rate for the industry load board, DAT. The model predicts the national dry van DAT spot rate over the coming 12 months. Variables for the model drew on 10 years of time series data measuring operational costs in the trucking industry, trucking market supply and demand, and changes in the U.S. economy.
The model uses machine learning to train on the 10 years of data to provide a short- and long-term prediction of the spot rate. The short-term (3 months) forecast captures immediate market disturbances (e.g., COVID-19) and works in tandem with the long-term multivariate forecast (12 months) to provide an accurate view of the expected market conditions.
Our forecasting model is accompanied by our Tactical Playbook to guide shippers through varied market conditions. The playbook addresses the pre-contract planning phase, the contract phase, and the post-contract tactical phase. The planning phase involves long-term elements that the shippers can focus on to foster higher tender acceptance rates and reduce rate instability. The contract phase actions guide the design of a shipper’s contract portfolio. Finally, the options for the tactical phase help with rapidly deployable steps that shippers can take to mitigate the costs associated with spot rate volatility.
Our machine learning model and Tactical Playbook allow shippers to transition from a defensive to an offensive position. The visibility into the future permits shippers to proactively design, plan, and manage their transportation needs in line with spot rate projections. This brings greater stability for shippers in the trucking game, and leads to stronger customer service, greater control of transportation costs, and improved stability of business operations.
Every year, around 80 students in the MIT Center for Transportation & Logistics’s (MIT CTL) Master of Supply Chain Management (SCM) program complete approximately 45 one-year research projects.
The students are early-career business professionals from multiple countries, with two to 10 years of experience in the industry. Most of the research projects are chosen, sponsored by, and carried out in collaboration with multinational corporations. Joint teams that include MIT SCM students and MIT CTL faculty work on real-world problems. In this series, we summarize a selection of the latest SCM research.