The buying behavior of the consumer is grown nowadays through recommender systems. Though it recommends, still there are limitations to give a recommendation to the users. In order to address data sparsity and scalability, a hybrid approach is developed for the effective recommendation in this paper. It combines the feature engineering attributes and collaborative filtering for prediction. The proposed system implemented using supervised learning algorithms. The results empirically proved that the mean absolute error of prediction was reduced. This approach shows very promising results.