This research has the objective of developing a model for the prediction of house prices in Ho Chi Minh City, Vietnam, using machine learning. The dataset used in our paper was obtained from commercial websites with relevant features of real estate objects such as land area in squared meters, number of floors, year of construction, the width of the street on which a house is located, and distance between the house and the city center. As for the Machine Learning model, we chose Linear Regression algorithm for the sake of straightforward implementation and interpretation. The K-fold cross-validation was applied to avoid overfitting. Data collection and preprocessing, such as outlier detection and transformation for exploratory data analysis were implemented, as well as feature engineering steps. The evaluation of the model was done by calculating common performance metrics such as Standard Error, R-squared and adjusted R-squared. The results provide good predictions for the prices of houses in the selected areas of the city and identify useful ideas for further research in the application of data mining and machine learning in the real estate sector in Vietnam.