In order to solve this exercise you will need the train and test csv files. train.csv contains ground-truth relevance features and the ground-truth relevance (derived from observing consumer's purchase decision) and needs to be used for model training, test.csv will be the basis for your submission.

File descriptions

- a_train.csv - the training set
- a_test.csv - the test set

Data fields

- srch_id: unique identifier for a search
- visitor_id: visitor id used to submit the search 
- visitor_visit_nbr: count of visits for the user who has submitted the search 
- visitor_loc_country: country of the user who has submitted the search 
- visitor_loc_region: region of the user who has submitted the search 
- visitor_loc_city: city of the user who has submitted the search 
- visitor_wr_member: indicates if the user who has submitted the search is part of the hcom loyalty program
- posa_continent: point of sale continent for a partiular search
- posa_country: point of sale country for a particular search
- srch_hcom_destination_id: destination id for a particular search 
- srch_dest_longitude: destination center longitude for a particular search
- srch_dest_latitude: destination center latitude for a particular search
- srch_ci: date of check-in of a search
- srch_co: date of cehck-in of a search
- srch_ci_day: day of check-in of a search
- srch_co_day: day of check-out of a search
- srch_los: length of stay of a search (check-in - check-out date)
- srch_bw: booking window of a search (search-date - check-in date)
- srch_adults_cnt: number of adults for a search 
- srch_children_cnt: number of children for a search 
- srch_rm_cnt: number of requested rooms on the search 
- mobile_bool: indicates if the search was submitted on a mobile browser
- mobile_app: indicates if the search was submitted on a mobile app
- device: identifies the device type type used for this search
- currency: currency relevant for the point of sale the search was submitted form
- travelad_bool: indicates if a porperty in a search was a paid advert
- dotd_bool: indicates if a property in a search was advertised as a special "daily deal"
- price_without_discount_local: discounted property price in local (posa specific) currency
- price_without_discount_usd: discounted property price in USD
- price_with_discount_local: non-discounted property price in local currency
- price_with_discount_usd: non-discounted property price in USD
- imp_drr: name of the pricing/discount rule relevant for this property
- booking_bool: indicates if property has been booken in a given search
- prop_key: unique property identifier
- prop_brand_bool: indicates if a property has a popular brand
- prop_starrating: conventional hotel star rating (1-5 Stars)
- prop_super_region: the super region this property belongs to (EMEA, APAC, NA, LATAM)
- prop_continent: continent this property is located on (Europe, North-America, South-America, ..... )
- prop_country: country this property is located in
- prop_market_id: higher granularity geo classification
- prop_submarket_id: highest granularity geo classification
- prop_room_capacity: max number of rooms this property has available
- prop_review_score: average guest review score for this property
- prop_review_count: count of customer reviews for this property
- prop_hostel_bool: indicates if a property is a hostel
- local_date: date for a particular search