The enormous data generated on daily basis amounts to big data technologies. This large amounts of data have knowledge and hidden patterns. Real estate turning out to be another biggest application in big data. The emphasis of this paper is to map the process involved in taking large amounts of data to predict the price of a house in real estate. The real estate sounds to be a long-term investment. In this paper, the housing Sale Data from Ames, Iowa is considered for the timeframe 2006–2010 with a view to construct relevant models to estimate the final sale price of a house. Due to high number of explanatory variables several models such as linear regression, random forest and gradient boosting models have been used as tools for feature selection to determine the statistically significant characteristics that influence the final sale price of a house. It has been observed that out of all the models, the gradient boosting model returned the efficient results.