Inferring Socioeconomic Characteristics from Travel Patterns

Nowadays, crowd-based big data is widely used in transportation planning. These data sources provide valuable information for model validation; however, they cannot be used to estimate travel demand forecasting models, because these models need a linkage between travel patterns and the socioeconomic characteristics of the people making trips and such a connection is not available due to privacy issues. As such, uncovering the correlation between travel patterns and socioeconomic characteristics is crucial for travel demand modelers to be able to leverage such data in model estimation. Different age, gender, and income groups may have specific travel behavior preferences. To extract and investigate these patterns, we used two data sets: one from the National Household Travel Survey 2009 and the other from the Metropolitan Washington Council of Government Transportation Planning Board 2007-2008 household survey. After preprocessing the data, a range of machine learning algorithms were used to synthesize the socioeconomic characteristics of travelers. After comparison, we found that the CatBoost model outperformed the other models. To further improve the results, a synthetic population and Bayesian updating were used, which considerably improved the estimation of income. This study showed that the conventional inference of travel demand from socioeconomic patterns can be reversed, creating an opportunity to utilize the plethora of crowd-based mobility data.