Estimating the flat price of land and buildings is a vital element. From ancient lands and buildings, the writings try to draw forth useful information. Machine-learning (ML) techniques are being used to analyze historical land and building transactions in an effort to identify trends that may be useful to both homebuyers and home providers. It is obvious that there is a huge price difference between flats in major metropolises and the least expensive neighborhoods. Technology that can forecast future home values must be developed since home prices rise yearly. Both developers and buyers can benefit from the prediction of home prices in determining when to make a property acquisition. The three criteria that most significantly affect a home's price are location, physical characteristics, and physical conditions. Considering that it can assist individuals in developing strategies for buying and selling homes, house price prediction is an essential tool. There are many current studies on predicting home prices. Existing research, however, does not allow for a thorough comparison and does not provide the most often used techniques for predicting home prices. This paper predicts house values using three state-of-the-art ML techniques and assesses the models. The proposed technique is Ridge regression for house price prediction. A dataset from the Kaggle platform was considered. According to experimental findings, Ridge regression has high accuracy for predicting home prices.