On April 11th, the Hujiang Economics and Management Forum Series (97th Session) was held at the Lecture Hall on the fourth floor of Building A of the Business School. Dr. Ke Wang, a lecturer from the Department of Information Management and Information Systems, delivered a lecture entitled “The Travel Demand Forecasting of Urban Public Transit System by Fusing Data from Multiple Sources”.
This report illustrated the importance of integrating multi-source data for forecasting urban public transportation demand based on the current multi-source information environment. Then, the existing traffic demand forecasting methods and defects were sorted out, a Probit-based SP-off-RP model was constructed, and the Gumbel distribution and its finite mixture were used to generate random numbers obeying the MEV distribution.The analytical approximation algorithm of the multivariate normal distribution was used to overcome the shortcomings of traditional estimation methods such as simulation integration and limited maximum likelihood estimation.Based on elasticity analysis, we can predict the public transportation market share under various transportation management policies and analyze the factors influencing Shanghai residents' commuting mode choices, providing decision support for implementing transportation management policies.
In conclusion, Dr. Zhonghui Hu, a lecturer in the Department of Business Administration, offered insightful commentary on the lecture. The event concluded with an engaging discussion among the participants, fostering a deeper understanding of the lecture’s content.
Translated by Wang Ke
Reviewed by Fang Zhiming