In this challenge you have to deal with a data set where most of the labels are missing, it falls into the category of semi-supervised learning, but unlabeled data is a majority. There is no test data, try to classify the training set and upload it here to see how it evaluates.
\r\nIn information security domain, anomaly detection gains its own importance from researchers day by day. It is discovered that occasionally emerged frauds or intrusions in modern information systems have incurred significant loss when the suspicious activities were not detected or inefficiently processed. Therefore, numerous efforts have been devoted to devise effective detection methods, and then proceed to automation of anomaly identification in real time.
\r\nIn this practical course, we challenge students with a set of well designated learning tasks, which require the participants to understand the task scenario entirely and to design their own algorithms to identify corresponding anomalies.
\r\nThe competition on discovering the anomalies will be conducted based on the performance of their algorithms.
\r\nDepartment of computer science, Chair of IT Security
\r\nSee details in Homepage ADCG SS'14
\r\nWe thank Prof.Dr.Claudia Eckert for supporting us on this practical course.
", "isPublished": false, "hasIsPublished": false, "postTitle": "", "hasPostTitle": false, "mimeType": "", "hasMimeType": false }, { "name": "Evaluation", "content": "The evaluation pages describes how submissions will be scored and how students should format their submissions. You don't need a sub-title at the top (the page title appears above). For an example of a high quality evaluation page, see the 2013 KDD Cup page, which we have copied here:
\r\nThe evaluation metric for this competition is Mean F1-Score. The F1 score, commonly used in information retrieval, measures accuracy using the statistics precision p and recall r. Precision is the ratio of true positives (tp) to all predicted positives (tp + fp). Recall is the ratio of true positives to all actual positives (tp + fn). The F1 score is given by:
\r\n\\[ F1 = 2\\frac{p \\cdot r}{p+r}\\ \\ \\mathrm{where}\\ \\ p = \\frac{tp}{tp+fp},\\ \\ r = \\frac{tp}{tp+fn} \\]
\r\nThe F1 metric weights recall and precision equally, and a good retrieval algorithm will maximize both precision and recall simultaneously. Thus, moderately good performance on both will be favored over extremely good performance on one and poor performance on the other.
\r\nFor every author in the dataset, submission files should contain two columns: AuthorId and DuplicateAuthorIds. DuplicateAuthorIds should be a space-delimited list. Every AuthorId counts as his/her own duplicate, and every duplicate should be listed under each of its respective ids. For example, if you suspect author A, B, and C are the same, you should list (A,A B C), (B,B A C), (C,C A B).
\r\nThe file should contain a header and have the following format:
\r\nAuthorId,DuplicateAuthorIds", "isPublished": false, "hasIsPublished": false, "postTitle": "", "hasPostTitle": false, "mimeType": "", "hasMimeType": false }, { "name": "rules", "content": "\r\n\t\r\n
1,1
8,8
9,9 10
10,10 9
etc.
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 5 entries per day.
\r\nYou may select up to 2 final submissions for judging.
\r\nStart Date: 5/27/2014 3:16 PM UTC
\r\nMerger Deadline: None
\r\nEntry Deadline: None
\r\nEnd Date: 6/9/2014 11:59 PM UTC
\r\n\t\r\nVisibility
\r\nThe competition is opened to public, although the general purpose is subject to a practical course hosted in Technische Universität München. All registered students are ought to submit their results online.
\r\nWhat is the team size?
\r\nThe team can be formed up to two registered students.
\r\nWhat are the credits?
\r\nOnly registered students in TUM can get credits in the end of competition. Non-participants of the practical course can as well get ranked by uploading results, if they are interested.
\r\nHow are the credits are evaluated?
\r\nParticipants (registered students) are required to take part in each session in class. They ought to present their results in public and also hand in a short report (maximal 2 pages). Credits are evaluated based on their performance and also the results.
\r\nHow to avoid cheating?
\r\nTeams are required to complete the challenges individually. If teams present similar reports/results, they are forced to proceed to a check-phase to defend themselves.
", "isPublished": false, "hasIsPublished": false, "postTitle": "", "hasPostTitle": false, "mimeType": "", "hasMimeType": false } ] }