 Predicting Housing Sale Prices Using Machine Learning with Various Data Split RatiosAwais Azam, Alimul Haque and Sakshi Rai Rai Data and Metadata, 2024, vol. 3, .231 Abstract: Introduction: Recent advancements in technology and data analytics have propelled the rapid growth of artificial intelligence (AI) and machine learning (ML), which are now central to various industries. These technologies have become essential tools in many sectors, especially in predictive modeling for asset pricing. Objective: From stock markets and rental properties to real estate and second-hand goods, AI and ML algorithms are widely applied to estimate values, optimize pricing strategies, and forecast market trends. Method: By analyzing vast amounts of data, these tools enable more accurate predictions and informed decision-making, revolutionizing traditional approaches to pricing and valuation. In this study, the primary goal is to achieve the most accurate price prediction for houses or apartments by experimenting with different data split ratios. Result: RMSE (House Price) 188965.28 is acceptable as best average price for houses. Conclusions: The value of RMSE of this model are relatively low and also the value Squared Correlation is 64% which is above the threshold of 50%, so the predicted price of this model is seems appropriate, so I have presented this model and its predicted house price as final acceptable value for my research outcome Date: 2024 There are no downloads for this item, see the EconPapers FAQ for hints about obtaining it. Related works: Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text Persistent link: https://EconPapers.repec.org/RePEc:dbk:datame:v:3:y:2024:i::p:.231:id:1056294dm2024231 DOI: 10.56294/dm2024.231 Access Statistics for this article More articles in Data and Metadata from AG Editor |
Is your work missing from RePEc? Here is how to contribute.
Questions or problems? Check the EconPapers FAQ or send mail to .
EconPapers is hosted by the
School of Business at Örebro University.