Overview
Public-transportation providers aim to use app-based incentives—both price-based and psychological—to activate customers, expand their travel radius, and shift travel toward off-peak periods. Fairtiq, with its innovative ticketing solutions, is well-suited and experienced in implementing incentive strategies at scale. However, broad, untargeted incentives (such as blanket price reductions or generic nudges) risk unsustainable revenue losses and low engagement due to heterogeneous customer propensities (e.g. price elasticities).
This research project develops a predictive segmentation tool that identifies customer groups most responsive to specific incentives, enabling precise, cost-efficient targeting that enhances both profitability and market share. Deploying Fairtiq’s rich transaction data combined with in-app survey responses, the tool applies supervised learning techniques to segment users by their likelihood to respond to financial and behavioral nudges.
The resulting incentive toolbox integrates monetary rewards (discounts, vouchers) and non-financial motivators (gamification, personalized feedback, social-engagement features). These instruments will be individually tested in collaboration with public-transportation partners. HSLU's research includes the definition of initial strategies, the specification and iterative optimization of the customer-segmentation algorithm (applying Bayesian hierarchical modeling), as well as the validation of the tool's cost-effectiveness, supporting its adoption and marketability. This approach offers a transformative opportunity for public transportation to increase modal share, boost revenue, and improve overall system sustainability.
