Deep learning model to predict the price of a car based on an input picture.
View Polygence scholar page
We seek to build a machine learning model to predict the price of a car given its image. For this task, we collected two original datasets of car images and their price. Using this as training data to train a convolutional neural network for regression, our project achieves sufficient accuracy in matching prices of car to images. Unlike previous models, this project focuses on cars specifically and utilizes a large dataset encompassing various car models. Since 1 in 3 Americans buy cars from online car dealerships, it is necessary that consumers can verify the price they see on the sites are legitimate. Alternatively, consumers could utilize this model to get the highest market value for a car they are trying to sell.