The patterns of user behavior are researched according to user logs.

The multidimensional features of users.

Search is at the heart of modern e-commerce. Traditional models optimize over a few hand-constructed features based on the item’s text. Now, there is a multimodal learning to rank model that combines these traditional features with visual semantic features transferred from a deep convolutional neural net work.

The Activity Feed (AF) is our taking on the ubiquitous “web feed” - a continuous stream of aggregated content, personalized for each user. These streams have become the defacto means of serving advertisements in the context of social media.

An online marketplace for handmade and vintage goods with over 30 million diverse listings, the problem of capturing the taste is particularly important - users come to the site specifically to find items that match their eclectic styles.