International Journal of Computer Applications |
Foundation of Computer Science (FCS), NY, USA |
Volume 186 - Number 37 |
Year of Publication: 2024 |
Authors: Manjusha Sanke, Yuvraj Naik, Ganesh Pillai, Rajat Ghode, Avinash Lamani |
10.5120/ijca2024923900 |
Manjusha Sanke, Yuvraj Naik, Ganesh Pillai, Rajat Ghode, Avinash Lamani . Machine Learning Powered Chatbot for Prediction of Used Car Price. International Journal of Computer Applications. 186, 37 ( Aug 2024), 8-13. DOI=10.5120/ijca2024923900
The used car market is a complex ecosystem influenced by various factors such as vehicle make, model, year, mileage, and condition. Predicting the price of a used car accurately requires a comprehensive understanding of these factors. In this paper, a machine learning-based approach is proposed to develop a chatbot that can predict the prices of used cars in India. To achieve this, three machine learning techniques namely Gradient Boosting, Random Forest, and Cat Boost have been used. The data for prediction is collected from reputable used car marketplaces such as OLX and Cars24, using web scraping tools like Scrapy and Selenium. The aforementioned techniques have been applied and compared on their respective performance to find the one that best suits the available dataset. Additionally, the model has been evaluated using test data and an accuracy of over 80% has been achieved. The chatbot interface has been provided which allows users to input car details and get real-time price estimates, helping them make informed decisions in the used car market.