The North American truckload (TL) market is characterized by inherent cyclicality, oscillating between periods of capacity surplus and shortage. This cyclicality creates significant uncertainty in capacity planning and pricing, making it difficult for market participants to anticipate shifts and respond effectively. This research develops a Logistic Regression-based early warning system to estimate the probability that the truckload market will shift into an expansionary or contractionary regime in a defined forecast horizon. Working in partnership with C.H. Robinson, we incorporate a diverse set of macroeconomic indicators and segment the analysis across Dry Van, Temperature Control, and Flatbed equipment types. Our methodology accounts for potential structural shifts in market behavior across pre-COVID, during-COVID, and post-COVID periods to evaluate whether traditional cycle dynamics remain valid in the current environment. Key findings indicate that specific leading indicators demonstrate predictive power for Dry Van and Temperature Control transitions, while Flatbed markets present unique challenges. The resulting probabilistic model provides a forward-looking tool for shippers, carriers, and brokers to shift from reactive market responses to proactive strategic
