Innovative Model for Forecasting Trailer Usage for Prefabricated Exterior Wall Panels

With growing demand for large scale exterior envelope prefabrication solutions beyond precast concrete, Engineer-to-Order (ETO) prefabrication firms must develop reliable methodologies to manage finish goods inventory of large components. The imbalance between fabrication time and installation requires ETOs to forecast likely consumption of transportation resources at the proposal stage with only a conceptual understanding of the final project. Since 2019 US domestic trucking costs have increased due to demand. Therefore, ETOs need a reliable forecasting trailer usage model for estimating transportation costs at the proposal phase and mitigate the risks of an arbitrary approach. The proposed model was developed and evaluated by using a supervised machine learning algorithm on a large data set collected from completed exterior prefabricated panel projects in the US. The model was then tested and compared to estimations completed by a professional prefabrication estimator. The model can assist ETOs with projecting the quantity of trailers likely necessary for a prefabricated panel project with less variance at the proposal phase with limited information. The increased accuracy can reduce the financial exposure of the ETOs.