Vongvanich, T. Sun, W. and Schmöcker, J.-D.(2023). Explaining and predicting station demand patterns using Google Popular Times data. Data Science for Transportation, 5(10).

Google Popular Times (GPT) data are a novel data source that is open to the public, accessible in real time and available in many cities around the world. We aim to explain and predict travel demand patterns for train stations in Kyoto city with these data. Stepwise multiple linear regression models are developed using popularity data to analyze the correlation of the station demand patterns and point of interest (POI) visitation rates in the station vicinity. Our linear regression models aim to identify POIs and POI types that have the highest impact on the demand at each station. To predict station demand, we compared different machine learning models with the multiple linear regression model and concluded that the best prediction performance is obtained by Gradient Boosting. We were able to identify influential POIs and quantify their impacts given that there are a sufficient number of POIs in the vicinity of the station. Our findings suggest that GPT data can enable transit planners and transit users to predict station demand in real time. City planners would also gain valuable insights into the activity types highly related to transit station demand. Moreover, the method can be scaled and applied to other types of transit stations in other cities.