Housing prices fluctuate daily and are frequently inflated rather than based on assessments, which makes the housing market society’s least transparent sector. Homebuyers use budgets and market strategies to find a new home. Nevertheless, the main problem with the existing method is that it does not predict future market trends, so it leads to a price rise. It is essential for the researcher to propose housing prices using real-world factors in the research. For clients to accurately predict a house’s price, they need to carefully consider the variables associated with the house, which is extremely challenging. To solve this problem, machine learning (ML) seems to be a viable option. In order to solve the issues, ML models such as Linear Regression (LR), Support Vector Machine (SVM), Random Forest (RF), and ensembles (LR, SVM, RF, K-Nearest Neighbor (KNN)) are used. Error metrics such as Mean Square Error, Root Mean Square Error, and Mean Absolute Error (MAE) are used to determine the best model. It was found that the combined Linear Regression (LR) and Random Forest (RF) model produces the least amount of error in this study. The error value should be as low as possible for a good regression model. This will allow people to compute a reasonable price for a house based on its most important attributes without having to depend on a broker to do this.