Characterizing favored users of incentive-based traffic demand management program

Incentive-Based Traffic Demand Management (IBTDM) provides monetary incentives to encourage commuters to alter their departures spatially or temporary with the goal of alleviating congestion. With the proliferation of smartphone technology, mobility apps have become ideal platforms for carrying out IBTDM. Tremendous amounts of empirical app usage data have been collected, but research into the behavioral insights of IBTDM remains limited. It is unclear who IBTDM's target users should be, and which users are the most likely to be stable (actively use the app) and behaviorally sustainable (willing to contribute to congestion alleviation). This study aims to profile the socio-demographics of such favored users based on behavioral and socio-demographic data collected by the Metropia app. The Ensemble Empirical Mode Decomposition (EEMD) method was used for usage trend detection. The detected usage trends were then used in pattern classification to identify stable and sustainable users. Next, binary logistic regression was adopted to explore the socio-demographic characteristics of each category of users. It was found that factors including home work days, household annual income, household size and schedule flexibility played important roles in users' usage patterns and departure time decisions. Specifically, home work days and household annual income co-influenced app usage patterns. Household size and schedule flexibility were the main determinants of departure time behavior. The findings of this research can be used to guide administrators of budget-constrained IBTDM programs who need to wisely allocate their marketing budget to increase penetration among favored users as to maximize the utility of the program.