The Data and Science Behind GrabShare Part I: Verifying Potential and Developing the Algorithm

This post details the initial approach to developing the GrabShare matching algorithm from the ground up, eschewing existing academic literature. It frames the problem as a constrained optimization problem with an objective function, constraints, and decision space. The post analyzes existing GrabCar booking assignment flows and extends them to GrabShare, introducing seat reservation constraints and defining user experience metrics like detour, ETA, and efficiency. It also presents an initial analysis of GrabCar booking data using DBSCAN clustering to verify the potential for ride-sharing.