Improved trip planning by learning from travelers' choices
Boris Chidlovskii · 2015
We analyze the work of urban trip planners and the relevance of trips they recommend upon user queries. We propose to improve the planner rec-ommendations by learning from choices made by travelers who use the transportation network on the daily basis. We analyze individual travel-ers ’ trips and convert them into pair-wise prefer-ences for traveling from a given origin to a des-tination at a given time point. To address the sparse and noisy character of raw trip data, we model passenger preferences with a number of smoothed time-dependent latent variables, which are used to learn a ranking function for trips. This function can be used to re-rank the top planner’s recommendations. Results of tests for cities of