This dataset represents a sample of 30 days of Criteo live traffic data. Each line corresponds to one impression (a banner) that was displayed to a user. For each banner we have detailed information about the context, if it was clicked, if it led to a conversion and if it led to a conversion that was attributed to Criteo or not. Data has been sub-sampled and anonymized so as not to disclose proprietary elements.
Use case
RL Agent for Real-Time Pacing and Bidding in a Demand-Side Platform
| Example observations | User & context uid_hash, timestamp, device_type, country, browser Inventory site_domain, site_cat, publisher_id, banner_size, placement Campaign campaign_id, ad_id, cost_type, payout_type History features (derived) #impr, #clicks, spend_so_far, budget_left(day), hour-of-day |
| Example actions | bid_price_bin pacing_factor (if budget control is included) |
| Example reward | revenue – cost, where revenue = conversion_value |