Route-Based User Segmentation and Clustering: A Machine Learning Approach for Enhanced Transportation Service

Advancements in machine learning have paved the way for innovative solutions in the realm of transportation. This paper presents a novel technique for sorting users based on their travel routes, with a versatile application in autonomous vehicles for intercommunication and enhanced passenger experiences. In this approach, real-time location data and route preferences of users are harnessed to dynamically group travellers sharing similar routes, fostering efficient communication and information sharing during transit. The method employs machine learning algorithms to analyze user trajectories and preferences, forming cohesive user clusters based on their common routes. Users within each cluster are seamlessly connected through an integrated communication platform, facilitating real-time interactions, sharing of route-specific updates, and mutual support. This innovative approach not only enhances the travel experience by promoting social connections among passengers but also holds the potential for improving route optimization, vehicle efficiency, and passenger safety within autonomous vehicle networks. Through extensive experimentation and validation, this technique demonstrates its efficacy in real-world scenarios, showcasing its adaptability and robustness for various modes of transportation. The findings underscore the promising implications of this approach in transforming the landscape of autonomous vehicles and public transportation by creating connected, informed, and engaged passenger communities.