The economy of a country or region relies vigorously on an efficient and dependable transportation system to provide accessibility and promote the safe and efficient movement of individuals and merchandise. In fact, the transportation framework has been identified by (Nicholson and Du 1997) as the most significant lifesaver in case of natural disasters, for example, earth shudders, floods, hurricanes, and others. Rebuilding of different life savers (for example water supply, electrical power system, sewer system, communication, and numerous others) depends emphatically on the capacity to ship individuals and equipment to harmed destinations. The real travel requests and street limit do differ over time, in this manner, adding to the vulnerability of travel times. With the expanded estimation of time, great loss is incurred by the drivers because of the unexpected schedule (either early or late) delay. A stable transportation system would give a serious edge in the worldwide economy. Therefore, the significance of the reliability of a transportation system cannot be overemphasized. Anticipating the traffic stream is an unpredictable procedure that is influenced by a few parameters, for example, traffic designs, information accumulation, applied zones, and so forth the rightness of traffic stream expectation can acquire preferred position to the smart traffic the executives, it can help in improving rush hour gridlock productivity and diminishing traffic blockage. Fundamentally, stream forecast targets is assessed the absolute number of vehicles given a particular district and a period interim. According to Boris S. [6] and Wei Shenet al. [69], the real-time speed of traffic flow is available to everyone thorough GPS. The traffic data providers use machine learning to predict speed for each road segment. Forecasting the real-time traffic knowledge is really helpful for traveler, it gives the potential of choosing better routes and helps in managing the transportation system.