Abstract The rapid advancements in information technology and intelligent systems within urban rail transit (URT) systems have highlighted the need for more personalized route recommendations that consider passengers’ travel habits. This study aims to address this issue by investigating passenger travel routes alongside other passengers who share similar travel preferences, utilizing collaborative filtering (CF) techniques. The approach involves analyzing historical card data to assess passenger travel profiles, including actual travel time under crowded conditions. By considering both individual passenger preferences and the preferences of similar passengers, a CF algorithm is employed to offer personalized route recommendations. The Shenzhen metro is used as a case study to illustrate the proposed method. The results demonstrate that the proposed approach surpasses traditional route recommendation methods by providing tailored suggestions that align more closely with passengers’ travel preferences. These findings emphasize the value of incorporating passenger travel preferences into route recommendation models, thereby enhancing the accuracy and effectiveness of personalized route recommendations within URT systems.
Personalized route recommendation for passengers in urban rail transit based on collaborative filtering algorithm
2024
Article (Journal)
Electronic Resource
Unknown
Metadata by DOAJ is licensed under CC BY-SA 1.0
Study on Route Choice Behavior of Urban Rail Transit Passengers
Trans Tech Publications | 2014
|Study of Passengers’ Route Choice of Urban Rail Transit Network under the Emergency
Trans Tech Publications | 2014
|An Ontology-Based Collaborative Filtering Personalized Recommendation
British Library Conference Proceedings | 2013
|Role of Passengers in a Modern Urban Rail Transit System
ASCE | 2013
|