Transportation systems are becoming increasingly complex, necessitating advanced analytical tools to support effective planning and operations. Analytics can be categorized into three types: descriptive analytics (summarizing past data), predictive analytics (forecasting future outcomes), and prescriptive analytics (recommending optimal actions). However, a crucial yet often overlooked aspect of analytics is interactivity, which allows decision-makers to dynamically adjust input parameters for real-time “what-if” scenario testing.

Interactive-OR is a proposed discipline that integrates Operations Research (OR) and Machine Learning (ML) to facilitate interactive analytics for transportation applications. This approach utilizes web-based platforms to distribute computational tasks between the front and back ends, ensuring speed and solution efficiency. This presentation will demonstrate the application of interactive analytics to key transportation challenges, including active transportation (bikeshare) network design and ridership prediction, on-street parking pricing optimization and occupancy prediction, last-mile planning and routing optimization, and transit shuttle service modeling.