An Intelligent Ride-Sharing Algorithm with Integrated Advertising Exposure for Enhanced MaaS Efficiency

Abstract

This paper proposes an advanced ride-sharing model within the framework of Mobility as a Service (MaaS), incorporating advertisement media exposure to optimize cost-effectiveness, system efficiency, and user engagement. In the context of increasing urban congestion and environmental concerns, the model enables efficient carpooling by matching routes using dynamic algorithms while delivering personalized advertisements to passengers. The system architecture comprises four main modules: basic route generation, passenger path prediction, carpool performance, and payment processing. These modules integrate features such as gaze-based discount incentives, eye-tracking sensors, and gamified events to increase advertisement visibility and user interaction. By blending real-time navigation data and predictive analytics, the system supports optimal route matching and estimated boarding times. A unique gamified discount model enhances user engagement by offering ride cost reductions based on interaction with advertisements. This study contributes to the evolving MaaS ecosystem by providing an algorithm that improves resource utilization, fosters multi-stakeholder cooperation, and lays the groundwork for AI-integrated transport solutions. The findings also offer valuable insights for future developments in decentralized, privacy-aware ride-sharing platforms.