International Research Journal of Engineering and Technology (IRJET)
e-ISSN: 2395-0056
Volume: 11 Issue: 04 | Apr 2024
p-ISSN: 2395-0072
www.irjet.net
Vahann Value: Used Car Price Prediction with Machine Learning and Interactive User Interface Smt B Sridevi1, G Kavya2, K Pavan Santosh Kumar3, K Divya Kalyan4, K Anil Uday Kiran5 1Assistant Professor, Dept. of CSE, GITAM (Deemed to be University), Visakhapatnam, Andhra Pradesh, India. 2,3,4,5Student, GITAM (Deemed to be University), Visakhapatnam, Andhra Pradesh, India.
---------------------------------------------------------------------***---------------------------------------------------------------------
Abstract – In this paper an innovative system that
including anticipated prices, evaluations of vehicle conditions, and forecasts of forthcoming market patterns. Given the dynamic nature of the used automobile market and the need for increased clarity and guidance, the proposed methodology aims to give users a deeper understanding of the factors influencing used car values.
accurately predicts the value of used vehicles is presented. By utilizing machine learning algorithms linear regression, decision tree and random forest on a comprehensive dataset of Indian car sales prices collected from Kaggle, our system provides precise and well-informed pricing decisions. It takes into account various influential factors such as brand, model, kms driven, fuel type, and year, enabling users and dealers to make informed choices. In contrast to manual valuations that are susceptible to biases and inaccuracies, this system offers a reliable framework for determining fair market values. Also, dealers can strategically set competitive prices, optimizing their buying and selling decisions in the ever-changing used car market. To further enhance user interaction with the predictive models and provide a smooth and user-friendly experience, an intuitive user interface is designed. The findings show that although all the algorithms are capable of forecasting used car prices, the Random Forest model performs better in terms of prediction accuracy. Additionally, the interactive user interface improves the system's usability and accessibility by enabling users to enter vehicle characteristics and get realtime price estimates. Overall, by combining machine learning algorithms with an interactive user interface, this project advances used car price prediction systems and provides a useful resource for both buyers and sellers in the automotive sector.
A game-changing development in the used car sector has been the creation of prediction systems that combine machine learning, data analysis, and real-time market trends in response to the growing demand for tools that support informed decision-making. These kinds of tools might completely change the way consumers make judgments about what to buy, help sellers fine-tune their pricing policies, and provide car enthusiasts a way to look at all of their alternatives when it comes to locating a used automobile that fits their needs and budget. This project aims to close the gap between consumers and sellers in the used car industry by utilizing cutting-edge technologies and data-driven insights. It does this by providing a dependable and user-friendly platform for navigating the difficulties of purchasing and selling preowned vehicles. This system aims to equip users with the necessary knowledge and tools to make educated decisions.
2. LITERATURE REVIEW A machine learning model for estimating used automobile values based on a variety of variables, including mileage, manufacture year, fuel consumption, and more, is presented in this paper. Several regression techniques were employed to the dataset, which was collected from used car listings. Random forest regression produced the best results, with an R-square of 0.90416. In comparison to earlier studies, the model offers a more thorough and precise prediction, which is beneficial for manufacturers, buyers, and sellers in the used automobile market. [1]
Key Words: Price prediction, Regression, Predictive model, Linear Regression, Decision Tree Regression, Random Forest Regression
1.INTRODUCTION Rapid technology breakthroughs and changing consumer demands have led to a major change in the automotive industry in recent years. The used-car market segment has grown significantly and now makes up a sizeable share of the entire automotive industry, which is one of the most remarkable changes. The reason for the recent rise in popularity of used cars is their affordability as well as the chance they present to purchase excellent pre-owned automobiles. But for both buyers and sellers, understanding the complexities of the used car market can be a difficult task. The principal aim of our project is to provide details of the used car market by providing readers with extensive knowledge on a range of topics,
© 2024, IRJET
|
Impact Factor value: 8.226
In their 2018 study, Monburinon and colleagues accumulated a broad dataset comprising 304,133 lines from a conspicuous German e-commerce stage, enveloping 11 unmistakable properties. Their essential objective was to figure utilized car costs utilizing different prescient strategies. For strong comparison, indistinguishable datasets were utilized for both preparing and testing over all models inspected. Strikingly, the investigation
|
ISO 9001:2008 Certified Journal
|
Page 221