There are problems in the Kyrgyz real estate market, such as a shortage of available data and there are also limitations in the use of analytical tools.Due to these problems, investors, sellers and buyers find it difficult to make decisions when choosing and purchasing real estate.This study is aimed at analyzing and forecasting real estate prices using machine learning methods.One of the first real estate House Price Prediction analyzing in Kyrgyzstan.A set of real estate data was collected, cleaned and processed, cleaned and prepared, and then a model was built and trained.Using a machine learning method such as random forest regression, key factors influencing prices were identified: the size of the object, the price per square meter and the number of rooms.The random forest model demonstrated high accuracy of forecasts with a coefficient of determination R^2 = 99%.Regression is deeply investigated even nowadays, to the point of still being worth of consideration in top journals (Jaqaman & Danuser, 2006; Altman & Krzywinski, 2015; Krzywinski & Altman, 2015).What Is R-Squared? R-squared (R2) is defined as a number that tells you how well the independent variable(s) in a statistical model explains the variation in the dependent variable. It ranges from 0 to 1, where 1 indicates a perfect fit of the model to the data.Numeracy, Maths and Statistics - Academic Skills Kit This study shows how machine learning can help to better analyze the real estate market in countries such as Kyrgyzstan.