Prediction plays an important role where we are trying to generate probable values for an unknown variable for each record in the new data, allowing the model builder to identify what that value will most likely be and where that value will be useful. Machine learning model predictions allow businesses to make highly accurate guesses as to the likely outcomes of a question based on historical data, which can be about all kinds of things – customer churn likelihood, possible fraudulent activity, and more. In this paper we are trying to present Path prediction methods and algorithms available and compare them. In this paper we are considering the Path prediction issues and problems during taxi and cab driving. In systems today, many drivers face issues while serving client requests during the drive because of many unpredictable events that. Similarly, although a person may shop on different days or at different times, they will often vision analyse the happen daily on the roads. In this paper, we try to find out more improved methods for alternate Path prediction and switching Paths due incidents and other unexpected events based on obstacle free Path prediction also allowing the reduction of delays. This paper reviews the literature regarding various machine learning models, algorithms & approaches focusing on Path prediction.We start by analyzing road network data collection algorithms and their efficiency.In the later part of the paper, we try to talk about metrics and parameters commonly used to evaluate prediction, in order to compare the different approaches. We list, detail and compare existing algorithms that provide Path predictions. This research leads to an understanding of advantages, disadvantages and trade-offs of the methods studied and will surely provide useful information for future development.