Artificial intelligence (including machine learning, data science, advanced analytics) has been successfully applied in many social and economic spheres, including weather forecasting, targeted political campaigns, automated detection of targets and events, optimization of system performance, and maximizing profits of various industries. In our work it is applied to predict and optimize Border Wait Time (BWT), which is one of the key performance metrics for the Agency.
A novel scientific approach is developed to allow the Agency to predict and minimize BWT. The approach consists of two stages. In the first (Traffic prediction) stage, hourly rate of vehicle arrival at the border is estimated from the historical data using traditional machine learning techniques such as regression and classification. In the second (BWT prediction) stage, BWT is estimated from the predicted traffic as a function of available resources (the number of lanes) using the queuing theory implemented through a computer simulation.