Housing is always the first issue for the common man in India. Everyone wishes to have housing in cities where there are opportunities such as education, employment, healthcare, infra. Hence, the investment and cost factor is of utmost importance for each individual and family in India. But the prediction of housing prices is a multi-dimensional activity based on several factors like location, size, and economic conditions. It is not always easy to make an estimate of the price of the property by calculating manually the parameters which affect in estimating the rate of the property. There is also the propensity for the customers to be deceived by real estate agents. They quote prices to the customers which are more than the real price. These kinds of price discrepancies raise confusion among the customers. Therefore, it is required to have a trust-worthy machine learning model predicting the housing prices depending on inputs required. This project entails application of Machine Learning algorithms for creating a model for housing price prediction. For this project, Random Forest Regression, and Gradient Boosting Regression will be utilized. These two models will then be stacked into CatBoost which will be a meta-model. CatBoost is an open-source library by Yandex that uses symmetric trees for making predictions. This project is based on a CSV dataset. The target variable, or price, is one of its approximately 22 features. The previously mentioned metrics Mean Absolute Error (MAE), Mean Squared Error (MSE), and R-Squared Score (R2) have been calculated in order to assess the model.