The increasing traffic congestion and environmental concerns in urban areas necessitate an innovative carpooling solution. Our goal was to develop a data-driven carpooling platform that leverages AI/ML algorithms to efficiently connect commuters, optimize routes, and reduce traffic congestion. This platform addresses challenges such as matching compatible users, calculating fares, predicting peak demand, ensuring safety, enabling transparent cost-sharing, and incentivizing carpooling during high-demand times.
One of the challenges we ran into was not having a dataset about preferences, routes (location), or time. To overcome this, using a Python script, we generated a dataset for preferences. For location, we used geo-cordinates, and time was calculated using a formula and these cordinates.
Tracks Applied (1)
Replit
Discussion