article · Concurrency and Computation Practice and Experience
Property valuation is inherently complex because pricing depends on numerous spatial and temporal factors, making fair and objective estimations difficult. While computer-aided valuation systems have improved real estate data analysis, many existing tools still suffer from low transparency, inefficiency, and inaccuracy. To address these issues, predictive modelling was examined by comparing machine learning with a traditional hedonic regression approach. Specifically, an Extreme Gradient Boosting algorithm was integrated with an outlier sum-statistic approach. Both the machine learning model and the hedonic regression model relied on thirteen input variables to forecast residential property values. When evaluated, the gradient boosting method demonstrated practical utility by achieving a prediction accuracy of 84.1 per cent, significantly outperforming the hedonic regression model, which reached an accuracy of only 42 per cent.
Real estate pricing plays an essential role in broader economic growth, yet standard valuation systems frequently struggle with inaccuracy and poor transparency. Demonstrating that machine learning models can double the accuracy of traditional hedonic approaches offers property evaluators, buyers, and financial organisations more reliable tools for assessing fair market values and managing financial risk.
The method targets automated property valuation for the real estate and financial sectors, where accurate price prediction informs lending, taxation, and investment decisions. With tested algorithmic models and reported accuracy figures based on thirteen inputs, the technology is at an applied and tested stage, though real-world deployment would require integration into commercial property software platforms.
AI-generated from the published abstract. Always read the original work before citing.
Summary The problem with property valuation is that it is extremely complex. It is difficult to objectively model the pricing process or fairly estimate a property value. Many factors can contribute to this complexity such as spatial and time factors. Evaluators and researchers have been trying to model the process for centuries. Up until recently, when computer‐aided valuation systems provided better solutions in the data evaluation and real estate valuation. Nevertheless, they may suffer from low transparency, inaccuracy, and inefficiency. This work explores the ability of machine learning techniques (MLTs) in enhancing economic activities by increasing the accuracy of house price prediction. In this article, XGBoost algorithm has been integrated with outlier sum‐statistic (OS) approach. In the real estate industry, the price of property plays a crucial role in economic growth. The research attempts to predict the price of a house using MLTs. Here, the price of the property is predicted using Extreme Gradient (XG) boosting algorithm and hedonic regression pricing. Both XGBoost and hedonic pricing models use 13 variables as inputs to predict house prices. The contribution of this research lies in the practicality of using XGboost technique to predict house prices. Finally, the accuracy of the prediction algorithms is reported with XGBoosting showing the highest accuracy of 84.1% while the accuracy of the hedonic regression algorithm is 42%.
This page summarises published work. The authoritative version sits with the publisher.
DOI: 10.1002/cpe.7342
Is something wrong with this record? Report it or request removal.
Discussion
Have you built on this work, tried to replicate it, or seen it applied in practice? Share what you know. Verified researchers and MARATTO™ domain experts can open a discussion, and any member can reply. Contributions are reviewed before they appear.
No discussion yet. Open the first thread.
New to MARATTO™? Create a free account.
