MACHINE LEARNING BASED ALGORITHMS FOR HOUSE PRICE PREDICTION IN REAL ESTATE
Faculty
Department
Year of Publication
upload
Publication Type
Abstract
The process of estimating property prices in Nigeria remains largely manual, subjective, and
inconsistent, as real estate valuation often depends on personal experience, incomplete records,
or unstructured web data. These limitations create inaccuracies that affect buyers, sellers,
investors, and policymakers. To address these challenges, this study aims to develop a more
reliable and data-driven method for house price prediction using machine learning techniques.
The objectives include collecting and preprocessing a multi-state Nigerian dataset, engineering
relevant features, developing multiple predictive models, and evaluating their performance to
identify the most accurate approach.
A dataset consisting of 28,915 property records scraped from PropertyPro was cleaned,
normalized, and transformed through techniques such as one-hot encoding and Mutual
Information Regression. Four machine learning models, which are Linear Regression, Decision
Tree, Random Forest, and XGBoost, were implemented and evaluated using MAE, MSE, and R².
Quantitatively, the models achieved R² scores of 0.475 (Linear Regression), 0.433 (Decision
Tree), 0.517 (XGBoost), and 0.520 (Random Forest). Qualitatively, Random Forest
demonstrated superior ability to capture nonlinear patterns, handle noisy data, and generalize
across diverse property locations. The best-performing model was deployed through a Streamlit
web application to enable real-time house price prediction for end users.
Despite its success, the study is limited by the absence of macroeconomic variables such as
inflation and interest rates, which play a substantial role in housing market dynamics.
Additionally, challenges in obtaining comprehensive and well-structured real estate data across
all Nigerian states constrained the breadth of the analysis. Future research should integrate
geospatial and macroeconomic datasets to further enhance prediction accuracy and model
robustness.
inconsistent, as real estate valuation often depends on personal experience, incomplete records,
or unstructured web data. These limitations create inaccuracies that affect buyers, sellers,
investors, and policymakers. To address these challenges, this study aims to develop a more
reliable and data-driven method for house price prediction using machine learning techniques.
The objectives include collecting and preprocessing a multi-state Nigerian dataset, engineering
relevant features, developing multiple predictive models, and evaluating their performance to
identify the most accurate approach.
A dataset consisting of 28,915 property records scraped from PropertyPro was cleaned,
normalized, and transformed through techniques such as one-hot encoding and Mutual
Information Regression. Four machine learning models, which are Linear Regression, Decision
Tree, Random Forest, and XGBoost, were implemented and evaluated using MAE, MSE, and R².
Quantitatively, the models achieved R² scores of 0.475 (Linear Regression), 0.433 (Decision
Tree), 0.517 (XGBoost), and 0.520 (Random Forest). Qualitatively, Random Forest
demonstrated superior ability to capture nonlinear patterns, handle noisy data, and generalize
across diverse property locations. The best-performing model was deployed through a Streamlit
web application to enable real-time house price prediction for end users.
Despite its success, the study is limited by the absence of macroeconomic variables such as
inflation and interest rates, which play a substantial role in housing market dynamics.
Additionally, challenges in obtaining comprehensive and well-structured real estate data across
all Nigerian states constrained the breadth of the analysis. Future research should integrate
geospatial and macroeconomic datasets to further enhance prediction accuracy and model
robustness.
Supervisor(s)
co-supervisor