Logo image
Predicting e-commerce item popularity using image quality features
Thesis   Open access

Predicting e-commerce item popularity using image quality features

Stephen Zakrewsky
Master of Science (M.S.), Drexel University
Jun 2016
DOI:
https://doi.org/10.17918/etd-6860
pdf
Zakrewsky_Stephen_20163.58 MBDownloadView

Abstract

Computer Science Computer Vision Electronic Commerce
In order to traverse the plethora of items for sale online, searching, ranking, and recommendation systems must be built, and the quality of these systems can make the difference between boom or bust. In all of these methods, being able to distinguish between popular and non-popular items is very important. Traditionally, these systems have only utilized textual metadata, however, images represent first order information to the shopper, and are composed of a variety of signals that shoppers respond to. In this thesis we look at the problem of predicting item popularity on a popular e-commerce site using image quality features, and show that these features provide complementary information to the textual features in making this prediction.

Metrics

58 File views/ downloads
16 Record Views

Details

Logo image