![\"\"](\"https://storage.googleapis.com/kaggle-media/competitions/kaggle/3504/media/expedia2.jpg\")
You cannot sign up to Kaggle from multiple accounts and therefore you cannot submit from multiple accounts.
\r\n\r\n Privately sharing code or data outside of teams is not permitted.\r\n It's okay to share code if made available to all participants on the forums.\r\n
\r\nTeam mergers are not allowed in this competition.
\r\n\r\nThere is no maximum team size.
\r\nYou may submit a maximum of 2 entries per day.
\r\nYou may select up to 1 final submissions for judging.
\r\nStart Date: 9/3/2013 5:03 PM UTC
\r\nMerger Deadline: None
\r\nEntry Deadline: None
\r\nEnd Date: 11/4/2013 11:59 PM UTC
\r\n\t\r\nThe data set and resulting model parameters are considered confidential information that cannot be shared with people who are not participating in the contest.
\r\nBy participating in this contest, you accept the competition rules.
", "isPublished": false, "hasIsPublished": false, "postTitle": "", "hasPostTitle": false, "mimeType": "", "hasMimeType": false }, { "name": "Description", "content": "\r\n
Expedia is the world’s largest online travel agency (OTA) and powers search results for millions of travel shoppers every day. In this competitive market matching users to hotel inventory is very important since users easily jump from website to website. As such, having the best ranking of hotels (“sort”) for specific users with the best integration of price competitiveness gives an OTA the best chance of winning the sale.
\r\nFor this contest, Expedia has provided a dataset that includes shopping and purchase data as well as information on price competitiveness. The data are organized around a set of “search result impressions”, or the ordered list of hotels that the user sees after they search for a hotel on the Expedia website. In addition to impressions from the existing algorithm, the data contain impressions where the hotels were randomly sorted, to avoid the position bias of the existing algorithm. The user response is provided as a click on a hotel or/and a purchase of a hotel room.
\r\nAppended to impressions are the following:
\r\n1) Hotel characteristics
2) Location attractiveness of hotels
3) User’s aggregate purchase history
4) Competitive OTA information
Models will be scored via performance on a hold-out set.
", "isPublished": false, "hasIsPublished": false, "postTitle": "", "hasPostTitle": false, "mimeType": "", "hasMimeType": false }, { "name": "Evaluation", "content": "The evaluation metric for this competition is Normalized Discounted Cumulative Gain.
\r\nNDCG@38 is per query and averaged over all queries.
\r\nHotels for each user query are assigned relevance grades as follows:
\r\nSubmissions for each user query should recommend hotels in order from the highest grade (most likely to purchase a hotel room) to the lowest grade (least likely to purchase a hotel room or click on the hotel).
\r\nSearchId,PropertyId\r\n2,7771\r\n2,26540\r\n2,25579\r\n2,7374\r\n2,131173\r\n2,37331\r\n2,27090\r\n2,12938", "isPublished": false, "hasIsPublished": false, "postTitle": "", "hasPostTitle": false, "mimeType": "", "hasMimeType": false }, { "name": "Timeline", "content": "
2,78858
2,30434
2,91899
2,3105
2,6399
3,130729
3,103937
3,55688
The timeline for this competition is simple: there are not multiple data releases and there is no model submission required prior to the end of the competition.
\r\nSample code to create the benchmarks is available on Github.
\r\nNote: test.csv does not contain the following columns: position, click_bool, gross_bookings_usd, nor booking_bool
\r\n\r\nYou can refer to www.expedia.com to better understand hotel search.
\r\n“Hotel” refers to hotels, apartments, B&Bs, hostels and other properties appearing on Expedia’s websites. Room types are not distinguished and the data can be assumed to apply to the least expensive room type.
\r\n\r\nMost of the data are for searches that resulted in a purchase, but a small proportion are for searches not leading to a purchase.
\r\nUsage of outside data is prohibited and modeling should focus fully on the given data.
\r\n\r\n| \r\n Column Name \r\n | \r\n\r\n Data Type \r\n | \r\n\r\n Description \r\n | \r\n\r\n \r\n | \r\n
| \r\n srch_id \r\n | \r\n\r\n Integer \r\n | \r\n\r\n The ID of the search \r\n | \r\n\r\n \r\n | \r\n
| \r\n date_time \r\n | \r\n\r\n Date/time \r\n | \r\n\r\n Date and time of the search \r\n | \r\n\r\n\r\n | \r\n
| \r\n\r\n site_id \r\n | \r\n\r\n\r\n Integer \r\n | \r\n\r\n\r\n ID of the Expedia point of sale (i.e. Expedia.com, Expedia.co.uk, Expedia.co.jp, ..) \r\n | \r\n\r\n \r\n | \r\n
| \r\n visitor_location_country_id \r\n | \r\n\r\n Integer \r\n | \r\n\r\n The ID of the country the customer is located \r\n | \r\n\r\n \r\n | \r\n
| \r\n visitor_hist_starrating \r\n | \r\n\r\n Float \r\n | \r\n\r\n The mean star rating of hotels the customer has previously purchased; null signifies there is no purchase history on the customer \r\n | \r\n\r\n \r\n | \r\n
| \r\n visitor_hist_adr_usd \r\n | \r\n\r\n Float \r\n | \r\n\r\n The mean price per night (in US$) of the hotels the customer has previously purchased; null signifies there is no purchase history on the customer \r\n | \r\n\r\n \r\n | \r\n
| \r\n prop_country_id \r\n | \r\n\r\n Integer \r\n | \r\n\r\n The ID of the country the hotel is located in \r\n | \r\n\r\n \r\n | \r\n
| \r\n prop_id \r\n | \r\n\r\n Integer \r\n | \r\n\r\n The ID of the hotel \r\n | \r\n\r\n \r\n | \r\n
| \r\n prop_starrating \r\n | \r\n\r\n Integer \r\n | \r\n\r\n The star rating of the hotel, from 1 to 5, in increments of 1. A 0 indicates the property has no stars, the star rating is not known or cannot be publicized. \r\n | \r\n\r\n \r\n | \r\n
| \r\n prop_review_score \r\n | \r\n\r\n Float \r\n | \r\n\r\n The mean customer review score for the hotel on a scale out of 5, rounded to 0.5 increments. A 0 means there have been no reviews, null that the information is not available. \r\n | \r\n\r\n \r\n | \r\n
| \r\n prop_brand_bool \r\n | \r\n\r\n Integer \r\n | \r\n\r\n +1 if the hotel is part of a major hotel chain; 0 if it is an independent hotel \r\n | \r\n\r\n \r\n | \r\n
| \r\n prop_location_score1 \r\n | \r\n\r\n Float \r\n | \r\n\r\n A (first) score outlining the desirability of a hotel’s location \r\n | \r\n\r\n \r\n | \r\n
| \r\n prop_location_score2 \r\n | \r\n\r\n Float \r\n | \r\n\r\n A (second) score outlining the desirability of the hotel’s location \r\n | \r\n\r\n \r\n | \r\n
| \r\n prop_log_historical_price \r\n\r\n\r\nposition | \r\n\r\n Float Integer | \r\n\r\n The logarithm of the mean price of the hotel over the last trading period. A 0 will occur if the hotel was not sold in that period. | \r\n\r\n\r\n\r\n | \r\n
| \r\n price_usd \r\n | \r\n\r\n Float \r\n | \r\n\r\n Displayed price of the hotel for the given search. Note that different countries have different conventions regarding displaying taxes and fees and the value may be per night or for the whole stay \r\n | \r\n\r\n \r\n | \r\n
| \r\n promotion_flag \r\n | \r\n\r\n Integer \r\n | \r\n\r\n +1 if the hotel had a sale price promotion specifically displayed \r\n | \r\n\r\n \r\n | \r\n
| \r\n gross_booking_usd \r\n\r\n \r\n srch_destination_id \r\n | \r\n\r\n Float \r\n\r\n \r\n Integer \r\n | \r\n\r\n Total value of the transaction. This can differ from the price_usd due to taxes, fees, conventions on multiple day bookings and purchase of a room type other than the one shown in the search | \r\n\r\n \r\n | \r\n
| \r\n srch_length_of_stay \r\n | \r\n\r\n Integer \r\n | \r\n\r\n Number of nights stay that was searched \r\n | \r\n\r\n \r\n | \r\n
| \r\n srch_booking_window \r\n | \r\n\r\n Integer \r\n | \r\n\r\n Number of days in the future the hotel stay started from the search date \r\n | \r\n\r\n \r\n | \r\n
| \r\n srch_adults_count \r\n | \r\n\r\n Integer \r\n | \r\n\r\n The number of adults specified in the hotel room \r\n | \r\n\r\n \r\n | \r\n
| \r\n srch_children_count \r\n | \r\n\r\n Integer \r\n | \r\n\r\n The number of (extra occupancy) children specified in the hotel room \r\n | \r\n\r\n \r\n | \r\n
| \r\n srch_room_count \r\n | \r\n\r\n Integer \r\n | \r\n\r\n Number of hotel rooms specified in the search \r\n | \r\n\r\n \r\n | \r\n
| \r\n srch_saturday_night_bool \r\n | \r\n\r\n Boolean \r\n | \r\n\r\n +1 if the stay includes a Saturday night, starts from Thursday with a length of stay is less than or equal to 4 nights (i.e. weekend); otherwise 0 \r\n | \r\n\r\n \r\n | \r\n
| \r\n srch_query_affinity_score \r\n | \r\n\r\n Float \r\n | \r\n\r\n The log of the probability a hotel will be clicked on in Internet searches (hence the values are negative) A null signifies there are no data (i.e. hotel did not register in any searches) | \r\n\r\n \r\n | \r\n
| \r\n orig_destination_distance \r\n | \r\n\r\n Float \r\n | \r\n\r\n Physical distance between the hotel and the customer at the time of search. A null means the distance could not be calculated. \r\n | \r\n\r\n \r\n | \r\n
| \r\n random_bool \r\n | \r\n\r\n Boolean \r\n | \r\n\r\n +1 when the displayed sort was random, 0 when the normal sort order was displayed \r\n | \r\n\r\n \r\n | \r\n
| \r\n \r\n | \r\n\r\n \r\n | \r\n\r\n \r\n | \r\n\r\n \r\n | \r\n
| \r\n comp1_rate \r\n | \r\n\r\n Integer \r\n | \r\n\r\n +1 if Expedia has a lower price than competitor 1 for the hotel; 0 if the same; -1 if Expedia’s price is higher than competitor 1; null signifies there is no competitive data \r\n | \r\n\r\n \r\n | \r\n
| \r\n comp1_inv \r\n | \r\n\r\n Integer \r\n | \r\n\r\n +1 if competitor 1 does not have availability in the hotel; 0 if both Expedia and competitor 1 have availability; null signifies there is no competitive data \r\n | \r\n\r\n \r\n | \r\n
| \r\n comp1_rate_percent_diff \r\n | \r\n\r\n Float \r\n | \r\n\r\n The absolute percentage difference (if one exists) between Expedia and competitor 1’s price (Expedia’s price the denominator); null signifies there is no competitive data \r\n | \r\n\r\n \r\n | \r\n
| \r\n\r\n comp2_rate \r\n | \r\n\r\n \r\n | \r\n\r\n \r\n | \r\n\r\n \r\n | \r\n
| \r\n comp2_inv \r\n | \r\n\r\n \r\n | \r\n\r\n (same, for competitor 2 through 8) \r\n | \r\n\r\n \r\n | \r\n
| \r\n comp2_rate_percent_diff \r\n | \r\n\r\n \r\n | \r\n\r\n \r\n | \r\n\r\n \r\n | \r\n
| \r\n comp3_rate \r\n | \r\n\r\n \r\n | \r\n\r\n \r\n | \r\n\r\n \r\n | \r\n
| \r\n comp3_inv \r\n | \r\n\r\n \r\n | \r\n\r\n \r\n | \r\n\r\n \r\n | \r\n
| \r\n comp3_rate_percent_diff \r\n | \r\n\r\n \r\n | \r\n\r\n \r\n | \r\n\r\n \r\n | \r\n
| \r\n comp4_rate \r\n | \r\n\r\n \r\n | \r\n\r\n \r\n | \r\n\r\n \r\n | \r\n
| \r\n comp4_inv \r\n | \r\n\r\n \r\n | \r\n\r\n \r\n | \r\n\r\n \r\n | \r\n
| \r\n comp4_rate_percent_diff \r\n | \r\n\r\n \r\n | \r\n\r\n \r\n | \r\n\r\n \r\n | \r\n
| \r\n comp5_rate \r\n | \r\n\r\n \r\n | \r\n\r\n \r\n | \r\n\r\n \r\n | \r\n
| \r\n comp5_inv \r\n | \r\n\r\n \r\n | \r\n\r\n \r\n | \r\n\r\n \r\n | \r\n
| \r\n comp5_rate_percent_diff \r\n | \r\n\r\n \r\n | \r\n\r\n \r\n | \r\n\r\n \r\n | \r\n
| \r\n comp6_rate \r\n | \r\n\r\n \r\n | \r\n\r\n \r\n | \r\n\r\n \r\n | \r\n
| \r\n comp6_inv \r\n | \r\n\r\n \r\n | \r\n\r\n \r\n | \r\n\r\n \r\n | \r\n
| \r\n comp6_rate_percent_diff \r\n | \r\n\r\n \r\n | \r\n\r\n \r\n | \r\n\r\n \r\n | \r\n
| \r\n comp7_rate \r\n | \r\n\r\n \r\n | \r\n\r\n \r\n | \r\n\r\n \r\n | \r\n
| \r\n comp7_inv | \r\n\r\n \r\n | \r\n\r\n \r\n | \r\n\r\n \r\n | \r\n
| \r\n comp7_rate_percent_diff \r\n | \r\n\r\n \r\n | \r\n\r\n \r\n | \r\n|
| \r\n comp8_rate \r\n | \r\n\r\n \r\n | \r\n\r\n \r\n | \r\n|
| \r\n comp8_inv \r\n | \r\n\r\n \r\n | \r\n\r\n \r\n | \r\n|
| \r\n comp8_rate_percent_diff \r\n | \r\n\r\n \r\n | \r\n\r\n \r\n | \r\n|
| \r\n \r\n | \r\n\r\n \r\n | \r\n\r\n \r\n | \r\n
![\"Expedia](\"https://storage.googleapis.com/kaggle-media/competitions/kaggle/3504/media/Picture1.jpg\")
![\"Property](\"https://storage.googleapis.com/kaggle-media/competitions/kaggle/3504/media/Picture2.jpg\")
![\"Trip](\"https://storage.googleapis.com/kaggle-media/competitions/kaggle/3504/media/Picture3.jpg\")
A number of participants will be invited to submit reports on their entries, and have an opportunity to discuss them at a workshop at ICDM.
\r\nThe winners of the competition will also be invited to write a paper on their entry and present it at the conference.
\r\nThe Prize Winner(s) will be notified and announced within 30 days of the end of the Competition.
\r\nThe First, Second, and Third place Prize Winner(s) will receive $12,000, $8,000, and $5,000, respectively.
\r\n", "isPublished": false, "hasIsPublished": false, "postTitle": "", "hasPostTitle": false, "mimeType": "", "hasMimeType": false }, { "name": "Winners", "content": "First Place
\r\nSecond Place
\r\nThird Place
\r\n