• Mr. Mayank Tiwari
• Rajneesh Pachouri
• Mr. Anurag Jain

: This Paper presents an advanced ensemble machine learning framework for electric vehicle (EV) price prediction, integrating Gradient Boosting and ExtraTrees regressors within a scalable three-layer architecture. Utilizing a comprehensive dataset of 14 key features—including battery capacity, range, seat configuration, and powertrain specifications—the proposed system achieves superior predictive accuracy with R² scores exceeding 0.95 and test Mean Absolute Errors of 1.47-1.69 across real-world EV market data characterized by skewed distributions. The methodology employs Python 3.12 backend processing with pandas and scikit-learn for robust feature engineering and normalization, followed by joblib serialization of trained models for production deployment. A Flask-based RESTful API with HTML5/JavaScript frontend enables real-time price forecasting through interactive web dashboards featuring accuracy visualization and seat count distributions. Comparative analysis demonstrates ensemble methods' superiority over traditional regressors, capturing nonlinear pricing dynamics through bias-variance tradeoff optimization via sequential boosting and randomized tree aggregation. Deployed as a production-ready system, this approach supports stakeholders in emerging markets with transparent, data-driven EV cost estimation for enhanced sustainability decision-making. This Paper presents an advanced machine learning framework for predicting electric vehicle (EV) prices using sophisticated ensemble regression techniques. We propose a hybrid approach combining Gradient Boosting Regressor and Extra Tree Regressor to predict EV prices with unprecedented accuracy. Analyzing 104 diverse EV models across 14 technical and market-driven features, our approach achieves 99.98% improvement in Mean Absolute Error (MAE: 1.4731) and 99.63% improvement in RMSE over traditional algorithms documented in the base IEEE paper. The integrated Flask web application enables real-time price forecasting, supporting manufacturers, consumers, and market analysts in the rapidly evolving EV ecosystem.

Electric Vehicles, Price Prediction, Ensemble Learning, Gradient Boosting, Extra Trees, Machine Learning, Regression Analysis, Web-based Application, Flask, Scikit-learn.

"Electric Vehicle Price Prediction Using Advanced Ensemble Machine Learning Models ", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.13, Issue 1, page no.c484-c491, January-2026, Available :http://www.jetir.org/papers/JETIR2601258.pdf

"Electric Vehicle Price Prediction Using Advanced Ensemble Machine Learning Models ", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.13, Issue 1, page no. ppc484-c491, January-2026, Available at : http://www.jetir.org/papers/JETIR2601258.pdf