In the realm of shared autonomous vehicle ride-sharing, the precise prediction is vital for optimizing resource allocation and improving travel efficiency. However, existing studies tend to overlook social attributes and demographic characteristics across various regions, resulting in disparities in prediction fairness between areas with plentiful and limited transportation resources. An innovative Social Graph Convolution Long Short-Term Memoty(SGC-LSTM) framework is proposed incorporating demographic, spatial, and transportation accessibility information into multiple functional graphs, including functional similarity, population structure, and historical demand graphs. Furthermore, fairness indicators are employed into the loss function to balance prediction accuracy and fairness, the findings indicate that there is an enhancement in both prediction accuracy and fairness by at least 8.9% and 11.1% respectively compared to base models. Furthermore, the predictions for rush hours in both privileged and underprivileged regions exhibit greater precision and rationality. The proposed framework could effectively capture the demands of diverse social groups, thereby contributing to the advancement of social equity.
Predicting Ride-Hailing Demand with Consideration of Social Equity: A Case Study of Chengdu
24.09.2024
465346 byte
Aufsatz (Konferenz)
Elektronische Ressource
Englisch
RIDE-HAILING SYSTEM, RIDE-HAILING METHOD, AND COMPUTER PROGRAM
Europäisches Patentamt | 2024
|Europäisches Patentamt | 2023
|Europäisches Patentamt | 2022
|