Real Estate Market Price Prediction Model of Istanbul

Abstract The Turkish Housing Market has experienced a steep increase in prices. Individual and corporate investors now possess tools to estimate the real estate evaluation while using smaller amounts of data with traditional techniques. Not having an analytical approach evaluate price could cause investor lose considerable money, especially case individual investors. This study aims determine how different machine learning algorithms market can improve this process. To be able test this, over 30000 lines housing 13 variables is scraped. Data cleansed, manipulated visualized, predictive models such as linear regression, polynomial decision trees, random forests, XGboost are created compared according CRISP-DM framework. results show that complex techniques create accuracy predicting listing prices houses. paper to: – analyze effects relatively large amount data, main contribute estate, compare find optimal one for market, accurate model predict value any house on Istanbul market.