This paper proposes a traffic shaping algorithm based on neural network, which adapts to a network over which streaming video is being transmitted. The purpose of this intelligent shaper is to eradicate all traffic congestions and improve the end-users video quality. It possesses the capability to predict, to a very high level of accuracy, a state of congestion based upon the training data collected about the networks behavior. Initially, the current traffic shaping technologies are discussed and later a simulation in a controlled environment is illustrated to exhibit the effects of this intelligent traffic-shaping algorithm on the underlying networks real time packet traffic and the eradication of unwanted abruptions in the streaming videos quality. This paper concluded from the results of the simulation that neural networks are a very superior means of modeling real-time traffic and that it can be applied as an appropriate solution to network congestion.