Real Estate Price Prediction and Analysis Using Voting Regression Compared with Linear Regression

The primary goal of this research work is to predict housing prices that are frequently overstated, using efficient machine learning algorithms obtain better accuracy. This study compares the price prediction accuracy Novel Voting Regression (Group 2) and Linear 1) algorithms. For each groups studied, sample size was N=10. Clincle used figure out size. pretest analysis maintained at 80%. Using G-power, calculated. Statistical yielded a value 0.584 for significance. method house 80.92%, which greater than algorithm’s 69.81%. Independent Sample T-test has statistical significance 0.584. So it can be concluded technique give near accurate values technique.