The YOOCHOOSE dataset contain a collection of sessions from a retailer, where each session is encapsulating the click events that the user performed in the session.
For some of the sessions, there are also buy events; means that the session ended with the user bought something from the web shop. The data was collected during several months in the year of 2014, reflecting the clicks and purchases performed by the users of an on-line retailer in Europe.
Use case
Real-time optimization of a product recommendation banner for an e-commerce site
| Example observations | Sequence of the last N item-id clicked Associated categories Time since the beginning of the session Current time-of-a-speed (day-week/hour) Click counter in the session Flag “has already bought” (derived from the “buy” file”) |
| Example actions | 100 k separate items (filterable to a candidate subset via heuristic or pre-screening model) |
| Example reward | 1 if the user clicks on the recommended item 5 bonus if the item is then purchased before the end of the session 0 otherwise (The weighting may be adjusted according to the product margin.) |