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\n\r\n Team mergers are allowed and can be performed by the team leader. In order to merge, the combined team must have a total submission count less than or equal to the maximum allowed as of the merge date. The maximum allowed is the number of submissions per day multiplied by the number of days the competition has been running.
\r\n
There is no maximum team size.
\r\nYou may submit a maximum of 5 entries per day.
\r\nYou may select up to 1 final submissions for judging.
\r\nStart Date: 1/11/2013 12:57 AM UTC
\r\nMerger Deadline: None
\r\nEntry Deadline: None
\r\nEnd Date: 2/20/2013 11:59 PM UTC
\r\n\t\r\nCompetition data may only be used for purposes of preparing an entry to the competition and may not be redistributed under any circumstances.
\r\nAdditional rules are \r\ndetailed here.
\r\nModel license agreement\r\nfor the winners.
", "isPublished": false, "hasIsPublished": false, "postTitle": "", "hasPostTitle": false, "mimeType": "", "hasMimeType": false }, { "name": "data-description", "content": "\r\n\r\n
There are six files in all: train.csv, test.csv,\r\nusers.csv, user_friends.csv, events.csv, and\r\nevent_attendees.csv.
\r\ntrain.csv has six columns: user, event, \r\ninvited, timestamp, interested, and not_interested. Test.csv contains the same columns as train.csv, except for interested and not_interested. Each row corresponds to an event that was shown to a user in our application.\r\n event is an id identifying an event in a our system. user is an id representing a user in our system. invited\r\nis a binary variable indicated whether the user has been invited to the event.\r\ntimestamp is a ISO-8601 UTC time string representing the approximate time (+/- 2 hours) when the user saw the event in our application. interested is a binary variable indicating whether a user clicked on the "Interested" button\r\n for this event; it is 1 if the user clicked Interested and 0 if the user did not click the button. Similarly,\r\nnot_interested is a binary variable indicating whether a user clicked on the "Not Interested" button for this event; it is 1 if the user clicked the button and 0 if not. It is possible that the user saw an event and clicked neither Interested\r\n nor Not Interested, and hence there are rows that contain 0,0 as values for \r\ninterested,not_interested.
\r\nusers.csv contains demographic data about our some of our users (including all of the users appearing in the train and test files), and it has the following columns: user_id, locale, birthyear, gender, joinedAt, location,\r\n and timezone. user_id is the id of the user in our system. locale is a string representing the user's locale, which should be of the form\r\nlanguage_territory. birthyear is a 4-digit integer representing the year when the user was born.\r\ngender is either male or female, depending on the user's gender. joinedAt is an ISO-8601 UTC time string representing when the user first used our application. location is a string representing the user's\r\n location (if known). timezone is a signed integer representing the user's UTC offset (in minutes).
\r\nuser_friends.csv contains social data about this user, and contains two columns: user and friends. user is the user's id in our system, and\r\nfriends is a space-delimited list of the user's friends' ids.
\r\nevents.csv contains data about events in our system, and has 110 columns. The first nine columns are event_id, user_id,\r\nstart_time,\r\ncity, state, zip, country,\r\n lat, and lng. event_id is\r\n the id of the event, and user_id is the id of the user who created the event. city,\r\nstate,\r\nzip, and\r\ncountry represent more details about the location of the venue (if known). lat\r\n and lng are floats representing the latitude and longitude coordinates of the venue, rounded to three decimal places. start_time\r\n is the ISO-8601 UTC time string representing when the event is scheduled to begin. The last 101 columns require a bit more explanation; first, we determined the 100 most common word stems (obtained via Porter Stemming) occuring in the name or description\r\n of a large random subset of our events. The last 101 columns are count_1,\r\ncount_2, ...,\r\ncount_100,\r\ncount_other, where\r\ncount_N is an integer representing the number of times the Nth most common word stem appears in the name or description of this event. count_other\r\n is a count of the rest of the words whose stem wasn't one of the 100 most common stems.
\r\nevent_attendees.csv contains information about which users attended various events, and has the following columns: event_id, yes, maybe, invited, and no. event_id\r\nidentifies the event. yes, maybe, \r\ninvited, and no are space-delimited lists of user id's representing users who indicated that they were going, maybe going, invited to, or not going to the event.
", "isPublished": false, "hasIsPublished": false, "postTitle": "", "hasPostTitle": false, "mimeType": "", "hasMimeType": false }, { "name": "Description", "content": "We (the competition hosts) are excited to sponsor the Event Recommendation Engine Challenge, which asks you to predict what events our users will be interested in based on events they’ve responded to in the past, user demographic information, and what events\r\n they’ve seen and clicked on in our app. The insights you discover from this data, and the algorithms the winners create, will allow us to improve our event recommendation algorithm, a core part of our applications and a key element in improving user experience.
\r\nThis is the first competition launching under the \r\nKaggle Startup Program!
", "isPublished": false, "hasIsPublished": false, "postTitle": "", "hasPostTitle": false, "mimeType": "", "hasMimeType": false }, { "name": "Prizes", "content": "Prizes are awarded to the teams finishing 1st, 2nd, and 3rd on the private leaderboard. The prizes are:
\r\nFor each user in the test set, you are submitting a list of events. These events should be ordered from the ones in which you predict the user will be most interested to those in which the user will be least be interested.
\r\nThe evaluation metric for this competition is Mean Average Precision at 200 (the maximum number of events for any one user is 116, so 200 doesn't create a meaningful limit). You can find more information about this evaluation metric on the\r\n\r\nKaggle wiki.
\r\nSample submission files can be downloaded from the data page. Submission files should be formatted as follows:
\r\nUser,Events", "isPublished": false, "hasIsPublished": false, "postTitle": "", "hasPostTitle": false, "mimeType": "", "hasMimeType": false }, { "name": "Timeline", "content": "
1776192,2877501688 1024025121 4078218285 2972428928 3025444328 1823369186 2514143386
3044012,2529072432 1532377761 1390707377 1502284248 3072478280 1918771225
4236494,152418051 4203627753 2790605371 799782433 823015621 2352676247 110357109
\r\n
January 10, 2013: Competition launches
\r\nFebruary 13, 2013: Public leaderboard frozen
\r\nFebruary 14, 2013: Public leaderboard answers released
\r\nFebruary 20, 2013: Deadline to make a submission on the private leaderboard
", "isPublished": false, "hasIsPublished": false, "postTitle": "", "hasPostTitle": false, "mimeType": "", "hasMimeType": false } ] }