Want an interview at Facebook? Facebook will review the top entries in the competition and offer you an interview if they like what they see. This is your opportunity to demonstrate your skills on a real-world social network dataset, and show them your creativity, open-mindedness and tenacity in the face of an open-ended predictive modeling problem.
\r\nThe challenge is to recommend missing links in a social network. Participants will be presented with an external anonymized, directed social graph (no, not Facebook, keep guessing) from which some edges have been deleted, and asked to make ranked predictions for each user in the test set of which other users they would want to follow.
Please note: You must compete as an individual in recruiting competitions. You may only use the data provided to make your predictions. Facebook will review the code of the top participants before deciding whether to offer an interview.
", "isPublished": false, "hasIsPublished": false, "postTitle": "", "hasPostTitle": false, "mimeType": "", "hasMimeType": false }, { "name": "rules", "content": "\r\n\t\r\nYou cannot sign up to Kaggle from multiple accounts and therefore you cannot submit from multiple accounts.
\r\n\r\n Sharing code or data outside of teams is not permitted.\r\n This includes making code or data made available to all participants, such as on the forums.\r\n
\r\nTeam mergers are not allowed in this competition.
\r\n\r\nThe maximum size of a team is 1 participant.
\r\nYou may submit a maximum of 2 entries per day.
\r\nYou may select up to 5 final submissions for judging.
\r\n\r\n Because the data can be manually decoded and thus an entry can be created by hand, scoring data will be withheld until you have locked down a model.\r\n
\r\n\r\n You must upload all kernels and model files alongside documentation in a single zip file\r\n in order for your entry to be eligible. You can do this at the time of submission, or append\r\n it to your submission at a later time (before the competition end).\r\n
\r\nStart Date: 6/5/2012 8:57 PM UTC
\r\nMerger Deadline: None
\r\nEntry Deadline: None
\r\nEnd Date: 7/10/2012 11:59 PM UTC
\r\n\t\r\nCompetitor agrees to grant and hereby grants to Competition Host a perpetual, irrevocable, worldwide, royalty-free, transferable, and sublicenseable right to use, review, reproduce, and internally distribute the Entry (including any and all submitted source code) in connection with evaluating Competitor’s suitability for employment, provided that the Entry licensed as set forth above will not be used for Competition Host’s commercial purposes except as may otherwise be set forth in this Agreement. Competitor agrees to execute any necessary documentation that Competition Host may reasonably require to effectuate the foregoing.
\r\nPlease note: You must compete as an individual in recruiting competitions
", "isPublished": false, "hasIsPublished": false, "postTitle": "", "hasPostTitle": false, "mimeType": "", "hasMimeType": false }, { "name": "Background", "content": "Facebook is hiring for multiple position within their Engineering Team. The job description below gives you an idea of what they normally look for in a data scientist.
\r\n\r\nFacebook Data Scientist Job Description
\r\nFacebook is seeking Data Scientists to join our Data Science team. Individuals in this role are expected to be comfortable working as a software engineer and a quantitative researcher. The ideal candidate will have a keen interest in the study of an online social network, and a passion for identifying and answering questions that help us build the best products.
\r\n
The evaluation metric for this competition is Mean Average Precision @ 10
\r\nSuppose there are m missing outbound edges from a user in a social graph, and you can predict up to 10 other nodes that the user is likely to follow. Then, by adapting the definition of average precision in IR (http://en.wikipedia.org/wiki/Information_retrieval, http://sas.uwaterloo.ca/stats_navigation/techreports/04WorkingPapers/2004-09.pdf ), the average precision at n for this user is
\r\n\r\nap@n = Σ k=1,...,n P(k) / min(m, 10)
\r\n\r\nwhere if the denominator is zero, the result is set zero; P(k) means the precision at cut-off k in the item list, i.e., the ratio of number of users followed up to the position k over the number k, and P(k) equals 0 when k -th item is not followed upon recommendation; n = 10
\r\nFor example,
\r\n(1) If the user follows recommended nodes #1 and #3 along with another node that wasn't recommend, then ap@10 = (1/1 + 2/3)/3 ≈ 0.56
\r\n(2) If the user follows recommended nodes #1 and #2 along with another node that wasn't recommend, then ap@10 = (1/1 + 2/2)/3 ≈ 0.67
\r\n(3) If the user follows recommended nodes #1 and #3 and has no other missing nodes, then ap@10 = (1/1 + 2/3)/2 ≈ 0.83
\r\nThe mean average precision for N users at position n is the average of the average precision of each user, i.e.,
\r\n\r\nMAP@n = Σ i=1,...,N ap@ni / N
", "isPublished": false, "hasIsPublished": false, "postTitle": "", "hasPostTitle": false, "mimeType": "", "hasMimeType": false }, { "name": "data-description", "content": "The code for the benchmarks may be downloaded from github.
\r\nThere are 5 files:
\r\ntest.csv contains a list of nodes in the social graph. For each node, recommend up to 10 other nodes for that user to follow.
\r\nSubmit a 2-column csv file. The first column (source_node) should contain an integer representing the nodes in test.csv, in the same order that they appeared in test.csv. The second column (destination_nodes) should contain a space-delimited series of between 0 and 10 integers, representing the 10 recommended nodes.
\r\nExample submission files may be downloaded from the data page.
", "isPublished": false, "hasIsPublished": false, "postTitle": "", "hasPostTitle": false, "mimeType": "", "hasMimeType": false }, { "name": "Prizes", "content": "Insert your prizes here
", "isPublished": false, "hasIsPublished": false, "postTitle": "", "hasPostTitle": false, "mimeType": "", "hasMimeType": false } ] }