Personalized Travel Recommendations Based on Asynchronous and Privacy-Preserving Mixed Logit Model

A data-secure and cost-efficient Personalized Travel Recommendation (PTR) is necessary to develop urban intelligence in transportation. Although prevalent machine learning-based methods have gained tremendous progress on PTR, Mixed Logit Model (MXL), as a mathematical method, is attracting much attention from industry and academia to analyze refined individual behavior for PTR. Since MXL is still in its infancy in PTR, it encounters three challenges that need to be resolved jointly, namely 1) how to use personal data to describe user preferences without violating user privacy, 2) how to utilize the idle computing resources at the edge to improve the estimation efficiency, and 3) how to coordinate devices whose capability and availability may change over time and space. To fill the gap, we propose an asynchronous and privacy-preserving mixed logit model (APMXL), which aims to integrate MXL with asynchronous federated learning (AFL), which can 1) non-intrusively exchange model parameters between the clients and the server without exposing the raw data, 2) separately perform local and global estimation at the client and server to optimize the load, and 3) collaboratively approximate the posterior of the standard MXL through a continuous asynchronous interaction mechanism. Moreover, based on a standard dataset, APMXL is evaluated, showing that the model accuracy is about 13% higher compared to a flat logit model. Meanwhile, the estimation time has been reduced by about 60% compared to a centralized MXL model, and the robustness of the model has been improved compared with the synchronous and privacy-preserving mixed logit model (SPMXL).