##Files * data.RDS - the training and test set data * sample_submission.csv - a sample submission file in the correct format In both, the training set and the test set, each row corresponds to a listing's impression at MercadoLibre. That means that the same item will appear many times on the data. The `conversion` column contains a boolean that specifies whether an order was attributed to that impression or not. In other words, it tells us if the user who was presented with that listing decided to purchase the item. ##Columns The following columns are available on the training set: * `accepts_mercadopago` Whether the item accepts Mercado Pago * `available_quantity` The available stock quantity at that moment * `avg_asp_item_bday` Average selling price of this item over the last days * `avg_asp_item_domain` Average price of items of the domain this item belongs to * `avg_asp_item_sel` Average price of seller sales * `avg_gmv_item_bday` average revenue generated by the item per day * `avg_gmv_item_domain_30days` Average revenue generated by the items of this domain on the last month * `avg_gmv_item_sel` Average revenue of items of this seller * `avg_gmv_seller_bday` Average revenue this seller makes by day * `avg_orders_item_bday` Average number of orders this item has by day * `avg_orders_seller_bday` Average orders the seller has by day * `avg_qty_orders_item_domain_30days` Average number of orders a random item of this domain made on the last month * `avg_qty_orders_item_sel_30days` Average number of orders an item of this seller makes on the last 30 days * `avg_si_item_bday` Average units sold this item has by day * `avg_si_item_sel_30day` Average units sold of an item of this seller on the past month * `avg_visits_item` Average visits this item had * `benefit` Ignore, should be dropped * `boosted` Whether the item was boosted * `buy_server_timestamp` Timestamp of the purchase * `category_id` Category of this item * `conversion` Target variable, it is True if this print has an attributed order * `cus_cust_id` Buyer id * `cus_cust_id_sel` Seller id * `date` Print date * `deal_print_id` Unique id for the print * `decimals` Ignore, will be dropped * `domain_id` Domain id for the item * `etl_version` Ignore, should be dropped * `free_shipping` Whether the item has free shipping * `fulfillment` Whether the item is fulfilled by MeLi * `full_name` Category full name * `health` Item health * `is_pdp` Whether the click landed on a PDP * `product_id` Product_id of the item * `item_id` ID of the item, useful for debugging * `listing_type_id` Whether the item is gold or not * `logistic_type` Logistic type for the item * `main_picture` URL for the main item picture * `offset` On which page the item was rendered * `original_price` Price from which the discount was done * `platform` Which platform the user is using * `price` Item price * `print_position` Position on the page * `print_server_timestamp` Timestamp for the print * `qty_items_dom` Number of items this domain has * `qty_items_sel` Number of items the seller has * `rn` Leftover from the ETL, Discard * `ROW_ID` Row of the submission file * `site_id` Site ID * `sold_quantity` Number of items sold at the moment of the print * `tags` Tags the item had at the moment of the print * `title` Item title * `total_asp_item_domain_30days` Average selling price of the items of the domain * `total_asp_item_sel_30days` Average selling price of all the items the seller sold on the last 30 days * `total_gmv_domain_30days` Total revenue the domain made on the last 30 days * `total_gmv_domain_bday` total_gmv_domain_30days / 30 * `total_gmv_item_30days` Total revenue made by the item on the lasts 30 days * `total_gmv_seller` Total revenue made by the seller on the last month * `total_items_domain` Number of items on the domain * `total_items_seller` Number of items the seller has * `total_orders_domain_30days` Total orders on the domain * `total_orders_item_30days` Total orders the Item had on the last 30 days * `total_orders_sel_30days` Total orders for the seller * `total_si_domain_30days` Total units sold of this domain * `total_si_item_30days` Total units sold of this item * `total_si_sel_30days` Same for the seller * `total_visits_domain` Total visits on this domain * `total_visits_item` Total visits this item had * `total_visits_seller` Total visits for this seller * `uid` session id * `user_id` user id * `warranty` Whether the item had warranty `conversion` should be predicted for those rows where `ROW_ID` is not missing.