Thursday, March 6, 2025 | 12:00 – 1:00 PM (ET)
Taxi and Transportation Network Companies (TNCs) are important components of the urban transportation system. An accurate short-term forecast of passenger demand can help operators better allocate taxi or TNC services to achieve a supply-demand balance in real time. As a result, drivers can improve the efficiency of passenger pick-ups, thereby reducing traffic congestion and contributing to the overall sustainability of the program. This study proposes a multi-task learning (MTL) model that selectively shares demand information between taxi and TNCs to improve short-term demand prediction accuracy. Using data from Manhattan, New York as a case study, the results demonstrated that the proposed MTL model outperforms the single-task learning model and other benchmarks for both transportation modes.
About the Presenters:
Dr. Yu Yu Zhang is a Professor with the Department of Civil and Environmental Engineering at the University of South Florida (USF). Dr. Zhang leads the Smart Urban Mobility Laboratory (SUM-Lab) at USF and serves as the Director for National Institute for Congestion Reduction (NICR), a USDOT National University Transportation Center. Dr. Zhang develops mathematical programming and solution algorithms, simulation tools, econometrics and statistical models, machine learning/deep learning methods for obtaining innovative solutions for more efficient, resilient, and sustainable multimodal transportation systems. Her recent efforts focus on challenging issues of emerging services and technologies in transportation, including Advanced Air Mobility and automated connected electrified and shared (ACES) Transportation.
Dr. Zhang is the recipient of 2020 Amazon Research Award, a prestigious research award supporting innovations at academic institutions and non-profit organizations worldwide and 2010 Fred Burggraf Award, which is conferred by the National Academies of Science Transportation Research Board for recognizing the excellence of young researchers. She has published more than 70 papers in top transportation journals such as Transportation Research Part B, Part C, Part D, and Part E (https://orcid.org/0000-0003-1202-626X).
Dr. Yujie Guo is a Data Scientist at Hyatt Hotels Corporation. Before joining Hyatt, he earned his PhD in Transportation Engineering from the University of South Florida. His dissertation is titled as ‘Data Driven Approaches for Understanding and Improving Urban Mobility’. His primary research interest focuses on leveraging artificial intelligence (AI) to address transportation challenges, including improving transportation efficiency, promoting equity, and understanding user behaviors. He specializes in time series forecasting, statistical modeling, causal inference, and both supervised and unsupervised learning techniques.
