One of the major source of global warming is the increasing use of automobiles which contributes to 30% in developed countries and 20% in developing countries. Globally, 15% of man made carbon dioxide comes from cars, trucks and other vehicles. Reducing transportation emissions is one of the most vital steps in fighting global warming and solutions to the transportation problem include usage of green vehicles and public transport modes. The traffic congestion and the delays in signals are the major causes for increasing pollution’s. The solution to this problem is presented in this paper. The effective use of big data analytic to analyze the emission rate and the time delays and total difference of a vehicles alternate path distance is calculated and the emission difference for the alternate path is calculated using machine learning algorithms. The optimized route must be efficient in reducing the time to reach and reduction of pollution, which is calculated for a route from source to destination in soft real-time using the map reduce technique. The standard emissions of vehicles are used to calculate the idle emissions and the running emissions of the vehicles for the current path with the congestion and also the alternative path to analyze the emissions in total to determine the path with least emissions. This paper proposes techniques for regulating the traffic by a dynamic signaling system as well as a new personalized alternate route alert system form a source to the destination.