The recent increase in technological changes to, Smartphone's have changed the lives of human beings. Whenever customers are purchasing smart phones, they examine a variety of factors such as the screen, processors, storage, camera, width, battery, accessibility, and so on. The most essential consideration that individuals overlook is if the product is worth the price. People fail to make the proper decision because there are no tools in place to cross-check the pricing. To solve this problem, many companies are at the moment are taking the help of machine learning strategies to take the correct decision. In this paper,We are using historical information on Smartphone essential features and costs to construct a model that will estimate the approximate price of the next Smartphone with decent accuracy. Different algorithms such as Linear Regression, KNN, LDA, Logistic Regression, and other different models are used to compute the price of smart phones. Optimized versions of Linear Regression and KNN algorithms are passed into a stacking classifier to generate a Hybrid Model which provided an accuracy of 94.8%. Bagging and Boosting Ensemble methods are also used to predict the accuracy and price of smart phones.