Personalized Context-Aware Multi-Modal Transportation Recommendation

TL;DR

This paper develops a personalized, context-aware multi-modal transportation recommendation system using various machine learning models on real-life trip data, highlighting the effectiveness of gradient boosting with SMOTE and insights into user preferences for metro travel.

Contribution

It introduces a novel approach combining multiple machine learning techniques for personalized transportation mode recommendation based on real-world data.

Findings

Gradient boosting with SMOTE outperforms other models.

Higher travel costs reduce mode utility across users.

Users tolerate longer metro trips more than other modes.

Abstract

This study proposes to find the most appropriate transport modes with awareness of user preferences (e.g., costs, times) and trip characteristics (e.g., purpose, distance). The work was based on real-life trips obtained from a map application. Several methods including gradient boosting tree, learning to rank, multinomial logit model, automated machine learning, random forest, and shallow neural network have been tried. For some methods, feature selection and over-sampling techniques were also tried. The results show that the best performing method is a gradient boosting tree model with synthetic minority over-sampling technique (SMOTE). Also, results of the multinomial logit model show that (1) an increase in travel cost would decrease the utility of all the transportation modes; (2) people are less sensitive to the travel distance for the metro mode or a multi-modal option that containing metro, i.e., compared to other modes, people would be more willing to tolerate long-distance metro trips. This indicates that metro lines might be a good candidate for large cities.