Personal Car Pooling Using Machine Learning

Abstract

The ever-increasing growth of cities has implied longer commuting distances (travel times) for their population and traffic congestion problems affecting public transport systems. These factors motivate the use of private vehicles causing an increase on traffic, longer idle times, reduced vehicle capacity utilization, higher mobility costs and a significant increase on vehicle emissions, one of today’s major environmental concerns. By having more people using one vehicle, carpooling reduces each person's travel costs such as fuel costs, tolls and the stress of driving. The datasets are processed using Dijkstra algorithm, KNN algorithm.