DEVELOPMENT OF A DATA-DRIVEN ENSEMBLE FRAMEWORK FOR VEHICLE PRICE PREDICTION IN NIGERIA USING MACHINE LEARNING ALGORITHMS

Abstract

The Nigerian used car market is marked by wide price fluctuations, limited pricing transparency, and inconsistent valuation practices, creating uncertainty for both buyers and sellers. This study sought to develop a reliable, data-driven predictive model tailored to the Nigerian automotive market using machine learning techniques. A comprehensive dataset of used vehicles advertised in Nigeria was used, including relevant attributes such as make, model, year of manufacture, mileage, engine capacity, fuel type, transmission type, vehicle condition, and location. The data underwent rigorous preprocessing, exploratory data analysis, and feature engineering to identify the most influential variables driving price variations. Six regression-based machine learning algorithms, Linear Regression, Ridge Regression, Lasso Regression, Decision Tree Regressor, Support Vector Regression, and Random Forest Regressor, were implemented and evaluated using standard performance metrics, including Mean Absolute Error (MAE), Root Mean Squared Error (RMSE), and the Coefficient of Determination (R²). Among the models tested, the Random Forest Regressor demonstrated superior predictive performance, achieving an R² score of 0.91 alongside the lowest RMSE. This result indicates improved predictive capability when compared with related studies conducted by Pudaruth (2023) and Breen et al. (2024). The findings further revealed that vehicle age, mileage, brand, engine size, and geographic location are the most significant determinants of used car prices in Nigeria. The developed model offers a practical and deployable solution for vehicle price estimation and can be integrated into dealership systems, online marketplaces, and private sales platforms. By enhancing price accuracy and transparency, this research strengthens market intelligence in Nigeria’s automotive sector and demonstrates the practical value of machine learning applications in emerging economies.