Project Abstract

With the vast amount of data available through the internet today, it is near impossible to search and find the best possible deal for you. With this project, I aim to see if AI can be used to replace this task by offering an instant price evaluation of your desired car. To achieve this, a data collection and cleaning pipeline needs to be created that feeds relevant car data into a machine learning model. This pipeline includes an automated data collection program built using Selenium and Beautiful Soup. The collected data contains nine relevant car features such as Make, Model, Mileage, and images. The collected data is then used to train machine learning models such as a random forest classifier and a pretrained image classifier model from Image Net. The final product empowers users with the models understanding of thousands of car listings, in a simple and usable interface.

Keywords: Machine Learning, Data collection pipeline, Neural Networks

 Conference Details

Session: Poster Session B at Poster Stand 74

Location: Sir Stanley Clarke Auditorium at Wednesday 8th 09:00 – 12:30

Markers: Matt Roach, Tom Owen

Course: BSc Computer Science, 3rd Year

Future Plans: I’m looking for work