Context
The dataset consists of three files: a file with behaviour data (events.csv), a file with item properties (item_properties.сsv) and a file, which describes category tree (category_tree.сsv). The data has been collected from a real-world ecommerce website. It is raw data, i.e. without any content transformations, however, all values are hashed due to confidential issues. The purpose of publishing is to motivate researches in the field of recommender systems with implicit feedback.
Content
The behaviour data, i.e. events like clicks, add to carts, transactions, represent interactions that were collected over a period of 4.5 months. A visitor can make three types of events, namely “view”, “addtocart” or “transaction”. In total there are 2 756 101 events including 2 664 312 views, 69 332 add to carts and 22 457 transactions produced by 1 407 580 unique visitors. For about 90% of events corresponding properties can be found in the “item_properties.csv” file.