In real-estate, prediction of a property’s value is challenging. Wrong prediction of property might affect capitalizing choices and financial planning of the investor. For predicting prices in real-estate, the authors applied three machine learning approaches. Authors have taken diverse dataset for training and validation of the machine learning techniques. The dataset contains several parameters like number of rooms, location of rooms, location of house, size of house, kitchen, washrooms, and other relevant characteristics. The authors utilized random forests, decision trees, and linear regression models for the prediction of real-estate prices. The linear regression model is the baseline model for the prediction due to its simple architecture. Decision trees find the non-linear correlation between the variables. Finally, random forest is applied to combine many decision trees which improve the accuracy and reliability of the work. For validation of the work, Root Mean Squared Error (RMSE), Mean, and Standard Deviation are calculated. As per experimental results, the random forest performed best compared to the decision tree and linear regression. Using random forest value of RMSE is calculated 1.38%, Mean error is calculated as 3.56%, and standard deviation is 0.98%.