Predicting the occupancy rates of truck parking locations : a machine learning approach

This study is conducted under the supervision of the province of Overijssel, which has engaged in a long-term program aimed at tackling truck parking issues. The aim is to develop an approach for using machine learning to predict the occupancy rates of truck parking locations. The research focuses on selecting the best-performing model configuration, based on a series of experiments. The resulting model uses a combination between time-dependent features and information about the occupancy earlier in the day as input. Evaluation of the model shows promising results and following this, a conceptual model for the deployment of the model into an integrated information system is proposed. The goal is to deliver the predictions to truck drivers, allowing them to use these in their decision-making process when selecting a parking location to drive to.