Scribd
Upload
49 views7 pages

Analysis and Prediction of Electric Vehicle CostsA Machine Learning Based Approach

This document presents a machine learning-based approach to predict electric vehicle (EV) costs, emphasizing the importance of cost analysis for EV adoption. It details the methodology, including data preprocessing, feature selection, and evaluation of various machine learning models to identify the most effective predictor. The study aims to enhance decision-making regarding EV investments by providing accurate cost predictions.

Uploaded by

jsatwik04
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PPTX, PDF, TXT or read online on Scribd
49 views7 pages

Analysis and Prediction of Electric Vehicle CostsA Machine Learning Based Approach

This document presents a machine learning-based approach to predict electric vehicle (EV) costs, emphasizing the importance of cost analysis for EV adoption. It details the methodology, including data preprocessing, feature selection, and evaluation of various machine learning models to identify the most effective predictor. The study aims to enhance decision-making regarding EV investments by providing accurate cost predictions.

Uploaded by

jsatwik04
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PPTX, PDF, TXT or read online on Scribd
You are on page 1/ 7

Analysis and prediction of

electric vehicle costs:A


machine learning-based
approach
This presentation explores how machine learning can predict the cost of
electric vehicles, helping us make informed decisions about the future of
transportation.
Team Members:

1. NAM LIKHITA PRAVALLIKA (21A31A4291)


2. JILAGAM N S SRINIVAS SATWIK (21A31A42B3)
3. KANTAMSETTI K SATYA PRASANNA (21A31A4283)
4. MADUPURI THANMAI SWECHITHA (21A31A4286)
5. PENKEY V S RAGHAVENDRA NEHRU (21A31A42C3)

Faculty Coordinator:

Mrs. R. Veera Meenakshi


Abstract
Electric vehicles (EVs) offer environmental benefits, but their adoption depends largely on cost. This research
leverages machine learning (ML) algorithms to predict EV prices by analyzing key cost-influencing factors
identified through literature review. A comparative analysis of popular ML algorithms was conducted to
determine the most accurate predictor. Theoretical validation and simulations were used to compare and
validate the findings. This study aims to enhance EV price prediction for informed decision-making.
Introduction
EV Adoption Cost Analysis
Electric vehicles are Understanding the
becoming increasingly factors influencing EV
popular as a sustainable costs is crucial for both
and efficient mode of consumers and
transportation. manufacturers.
Existing System
Traditional Approach Limitations
The system is designed to • Small Dataset
predict EV prices based • Overfitting Issues
on critical features such
• Scalability Concerns
as brand, model,
• Execution Time
acceleration, range,
Discrepancies
battery backup,
efficiency, and other • Limited Exploration
vehicle specifications.
Model Training and Evaluation

Model Selection
Algorithms such as linear regression, decision trees, and neural networks
1
are considered for their suitability to EV cost prediction.

Training
2 The model is trained using historical data to identify patterns and
relationships influencing EV costs.

Evaluation
3 Performance metrics such as accuracy, precision, and
recall are used to assess the model's effectiveness in
predicting costs.
Proposed System

Data-Driven Approach
The proposed system leverages machine learning to analyze a comprehensive dataset of EV costs and influencing factors.

Key Factors Analyzed :


• Brand

• Acceleration

• Top Speed

• Range

• Battery Backup
Methodology

Data Preprocessing:
• Normalization

• Encoding categorical variables

• Splitting into training/testing sets

Feature Selection:
Identifies the most cost-influencing variables.

Machine Learning Models Evaluated:


• Linear Regression

• Decision Trees

• Random Forests

• Support Vector Machines (SVM)

• Artificial Neural Networks (ANN)

Best Model:
Selected based on accuracy and performance metrics.

You might also like