This note provides a solution to vehicle’s compound allocation problem. It has been treated as a classification task employing different Machine Learning (ML) algorithms. It is performed using the known car attributes and the time that vehicles have spent in the compound region, i.e., inventory warehouse, waiting the customer delivery day. Classification results have been assessed with F1 Score and CatBoost has arisen as the best technique, with values larger than 70%. Finally, reallocation strategy has been tested and outcomes exhibit that company’s expert performance is equaled or overcame with respect to time distribution.