A Machine Learning Approach for Forecasting Energy-Driven Automobile Tariffs

A Machine Learning Approach for Forecasting Energy-Driven Automobile Tariffs

 Mr. Vinay patel G L1,  Sanjay B K 2

1Assistant Professor, Department of MCA, BIET, Davanagere

2Student,4th Semester MCA, Department of MCA, BIET, Davanagere

ABSTRACT

Although electric vehicles (EVs) have many benefits for protecting the environment and lowering emissions, their widespread adoption mainly depends on their price. With machine learning (ML) algorithms, costs can be predicted. This research aims to compare the performance of some of the most well-known ML algorithms to determine which algorithm will best predict the price of electric vehicles. To identify the key characteristics, we examined the literature to research the elements that determine the price of electric vehicles in order to estimate their cost. We theoretically compared these ML algorithms to validate our findings and then compared the output of this comparative study to the outcomes of the simulations. The rapid adoption of electric vehicles (EVs) is reshaping the automotive industry, driven by technological advancements and growing environmental concerns. This project, titled "Electric Vehicle (EV) Price Prediction using Machine Learning," leverages advanced regression models to predict EV prices based on a comprehensive set of features. Utilizing Python as the backend coding language and deploying the solution through a Flask-based web framework with a user friendly front end comprising HTML, CSS, and JavaScript, the project integrates advanced machine learning   techniques to achieve accurate price predictions.

The study employs two robust regression models: Gradient Boosting  Regressor and Extra Tree Regressor. The Gradient Boosting Regressor achieved a Training Set Mean Absolute Error (MAE) of 0.1917 and a Test Set MAE of 1.4731, while the Extra Tree Regressor achieved a perfect Training Set MAE of 0.000 and a Test Set MAE of 1.6941. These models were trained and tested on a comprehensive dataset containing 14 key features: Brand, Model, Acceleration, Top Speed, Range, Efficiency, Fast Charge, Rapid Charge, Power Train, Plug Type, Body Style, Segment, Seats, and Price in Euro. These features encompass various aspects of EV specifications, performance, and market classification, providing a comprehensive basis for price prediction.

Keywords: Conventional pricing, Electric vehicles.