Abstract :

The Used Car Market Is A Rapidly Growing Multi-billion-dollar Industry Where Accurate Vehicle Valuation Plays A Crucial Role For Both Buyers And Sellers. However, Traditional Pricing Approaches Often Lack Consistency, Transparency, And Accuracy, Leading To Information Asymmetry And Potentially Unfair Transactions. This Project Aims To Overcome These Challenges By Developing A Machine Learning-based Vehicle Price Prediction System That Delivers Reliable And Data-driven Price Estimates. The Proposed System Utilizes A Gradient Boosting Regressor Trained On A Comprehensive Dataset Containing Key Vehicle Attributes Such As Brand, Model, Manufacturing Year, Mileage, Engine Size, Fuel Type, Transmission Type, And Overall Condition. The Methodology Follows A Structured Pipeline That Includes Data Collection, Preprocessing, Exploratory Data Analysis (EDA), Feature Engineering, Model Training, And Performance Evaluation. The Trained Model Demonstrates Strong Predictive Capability, Achieving An R² Score Of 0.93 And A Root Mean Squared Error (RMSE) Of Approximately 28,457 On The Test Dataset. Feature Importance Analysis Highlights That Factors Such As Vehicle Age (year), Mileage, And Engine Size Significantly Influence Pricing.

Published:

06-4-2026

Issue:

Vol. 26 No. 4 (2026)

Page Nos:

1312-1319

Section:

Articles

License:

This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.

How to Cite