Naren Chittar

A study on the impact of product images on user clicks for online shopping

In this paper we study the importance of image based features on the click-through rate (CTR) in the context of a large scale product search engine. Typically product search engines use text based features in their ranking function. We present a novel idea of using image based features, common in the photography literature, in addition to text based features. We used a stochastic gradient boosting based regression model to learn relationships between features and CTR. Our results indicate statistically significant correlations between the image features and CTR. We also see improvements to NDCG and mean standard regression.

Assessing product image quality for online shopping

Assessing product-image quality is important in the context of online shopping. A high quality image that conveys more information about a product can boost the buyers confidence and can get more attention. However, the notion of image quality for product-images is not the same as that in other domains. The perception of quality of product-images depends not only on various photographic quality features but also on various high level features such as clarity of the foreground or goodness of the background etc. In this paper, we define a notion of product-image quality based on various such features. We conduct a crowd-sourced experiment to collect user judgments on thousands of eBays images. We formulate a multi-class classification problem for modeling image quality by classifying images into good, fair and poor quality based on the guided perceptual notions from the judges. We also conduct experiments with regression using average crowd-sourced human judgments as target. We compute a pseudo-regression score with expected average of predicted classes and also compute a score from the regression technique. We design many experiments with various sampling and voting schemes with crowd-sourced data and construct various experimental image quality models. Most of our models have reasonable accuracies (greater or equal to 70%) on test data set. We observe that our computed image quality score has a high (0.66) rank correlation with average votes from the crowd sourced human judgments.

Mining product intention rules from transaction logs of an ecommerce portal

In this paper, we address the following problem: In the context of an ecommerce portal with product based inventory, predict the product p the user is interested, when he/she issues a query q. A viable solution to the above problem is necessary for e-commerce portals to a:) increase the relevance of their search results and b:) provide high quality recommendations. Higher quality search results and recommendations foster user purchases and thereby leading to increased revenue. We propose a rule based framework that maps a users query to a product. We propose a systematic search strategy that mines product intention rules from transaction logs of an ecommerce site. We validate the efficacy of the rules by running extensive experiments. Our results show that our approach produces product intention rules with high accuracy and coverage.

A Short-Term Bookmarking System for Collecting User-Interest Data

During the shopping process, users typically narrow down their search to a small collection of products before making a final purchase. These data, consisting of products that users are considering purchasing, correlate strongly with user search intent and product desirability. By allowing users to bookmark products between browsing and purchasing, we collect user-interest information. We then propose a product recommendation algorithm based on these data. By considering both popular and long-tail queries, we shed light on the potential usage of the data.