Behavior change requires more than a mindshift shift. Our MaaS platform’s use of dynamic and personalized incentives are tailored to individual preferences and interests. The following overview and case study shows how it works.
Metropia's behavior change approach is designed to be progressive and incremental, guiding users through a series of steps to encourage sustainable transportation choices. The journey begins with a loyalty program that focuses on fostering user engagement and ensuring a high rate of return. By offering incentives and rewards for consistent usage of the platform, Metropia aims to establish a strong foundation of user loyalty.
Building upon this foundation, occasional challenge programs are introduced to nudge users towards trying different non-driving modes of transportation. These challenges serve as opportunities for users to explore alternative modes that they may not have considered or experienced before. By gradually expanding their repertoire of transportation options, users become more receptive to embracing sustainable modes of travel.
As users become more comfortable and receptive to change, Metropia leverages dynamic and personalized incentives to encourage specific behavioral shifts. For example, users may receive offers to adjust their departure times, either leaving earlier or later, or to consider switching to other familiar and appealing modes of transportation. These offers are tailored to individual preferences and needs, motivating users to make informed decisions that benefit both themselves and the overall transportation system.
As shown in Figure 1, through this progressive approach, Metropia creates a gradual and sustainable transition towards sustainable transportation choices. By starting with a loyalty program, progressing to challenge programs, and ultimately employing dynamic and personalized incentives, Metropia empowers users to embrace alternative modes of travel, reduce their reliance on driving, and contribute to a more efficient and sustainable transportation ecosystem.
Figure 1: Progressive and Babystep Behavior Change Process
How it Works
Dynamic and personalized incentives are enabled through our Incentivization Architecture which incorporates the Metropia Massive Mobility Management (M4) module, which dynamically generates personalized incentives in real-time. Developed by the experienced Metropia team, M4 utilizes academic research to provide individualized incentive offers for departure time and mode change. Figure 2 outlines the three main sub-modules of M4: User Informatics, Modeler, and Solver. The User Informatics sub-module maps a user's daily activity pattern, trip trajectories, and incident impact area to identify those who are targeted for dynamic incentives. The Modeler and Solver sub-modules collaborate to determine optimal incentive recommendations based on campaign objectives and information from the MOD module. Once the final solution is obtained, the M4 module transmits the recommendation to the Incentive Engine (IE), which communicates the recommended options and the value of the offered incentive to individual users. This approach, similar to the implementation in Bay Area Rapid Transit's (BART) PERKS 2 program by the Metropia team, ensures cost-effective incentives aligned with the stated goals
Figure 2: M4 Framework
Metropia's ai-backed platforms transformed the BARTPerks program by implementing personalized incentive offers, targeting optimal audiences, and increasing program participation while reducing operational costs. The process involved predicting daily time-dependent crowding patterns using machine-learning algorithms based on data sources like Clipper Card data, weather data, and special event data. Metropia's behavior platform then determined new departure times for riders within a 40-minute window of their routine departure time, considering the balance between the imposition on riders and the benefit to the system. Reward points were offered based on the calculated impact. INDUCE monitored users' adherence to the recommended departure time using Clipper Card data, awarding points accordingly. Additional opportunities to earn reward points included using BART for weekend activities, airport-bound trips, and participating in in-app surveys. Users could redeem their points for various gift cards through the Perks 2 section of the BART app, enhancing the overall user experience.
By comparing incentivized participants to the control group, it was observed that participants increased their share of travel during the morning rush by 6% in less congested earlier periods and by 19% in less congested later periods. In the afternoon, incentives led to a 13% increase in participant travel during less congested earlier periods and a 20% increase during less congested later periods.
The average incentive cost per shifted trip to a less crowded time period was approximately $1, which then freed up a seat during peak periods, making it available to an additional paying passenger. This cost compared favorably to the average one-way fare of $4 for a typical commuter.
According to the final report of the pilot program, scaling up the initiative to reduce crowding by 5% would have the equivalent effect of freeing up 30 train cars, at just 1/3 the cost of purchasing and maintaining those cars ($1.9 million compared to $6 million).