INTERNATIONAL RESEARCH JOURNAL OF MODERNIZATION IN ENGINEERING TECHNOLOGY AND SCIENCE

Abstract

This research paper explores the development and implementation of a machine learning model for predicting used car prices based on various features. The project involves preprocessing and analyzing a dataset consisting of car attributes and prices, followed by the creation and deployment of a linear regression model. The study aims to demonstrate the effectiveness of machine learning in the automotive industry and showcases the practical application of predictive analytics. The research begins by collecting and preprocessing the dataset, which includes features such as car brand, manufacturing year, mileage, fuel type, seller type, transmission, owner status, engine specifications, and seating capacity. Preprocessing involves handling missing values, removing duplicates, and converting categorical data into numerical format suitable for machine learning. Next, data analysis is performed to understand the distribution and significance of different features. This includes identifying important columns for model training and splitting the dataset into training and testing subsets. The linear regression model is then trained using the training dataset to learn the relationship between input features and car prices. The trained model is evaluated using the testing dataset to assess its predictive performance. Predictions are made based on user input through a web application interface, demonstrating real-time price estimation for different car configurations. The model's accuracy is validated by comparing predicted prices with actual prices from the dataset. Furthermore, the research discusses the deployment of the machine learning model as a web application using Streamlit, allowing users to interactively input car specifications and receive instant price predictions. The paper concludes by highlighting the implications and potential applications of such models in the automotive industry, emphasizing the importance of data-driven decision-making and predictive analytics in optimizing pricing strategies. Overall, this research provides insights into the entire process of developing and deploying a machine learning model for car price prediction, demonstrating its accuracy and practical usability. The project contributes to advancing the field of predictive analytics in the automotive sector and underscores the value of data-driven approaches in enhancing business decision-making processes.

Paper File to download :