When studying for a test, you want to know how well you're going to do. More specifically, you want to know what areas you need to study more. In order to help students answer this question, we are attempting to predict their probability of answering questions\r\n correctly. The data in this competition comes from students studying for three tests: the GMAT, SAT, and ACT.
\r\nYou are attempting to predict, for each question attempted in the test set, whether the student will answer the question correctly. To succeed, you will need to improve on the state-of-the-art in student evaluation. While the questions included labels\r\n indicating their specified test area, there may be structure which helps better organize the areas of knowledge involved in each question. In the short term, this will help students figure out what areas they are weak in; but ultimately, this will help create\r\n tests to better measure what a student actually knows.
\r\nThe prize pool is $5,000 ($3,000 for first, $1,500 for second and $500 for third), with entries judged using\r\nCapped Binomial Deviance.
", "isPublished": false, "hasIsPublished": false, "postTitle": "", "hasPostTitle": false, "mimeType": "", "hasMimeType": false }, { "name": "data-description", "content": "Data description
\r\nThe fields of the data are as follows (the mappings from category fields to numeric values are in category_labels.csv):
\r\nTest data does not include answer_id or outcome (from which correctness could be determined).
\r\nTest/training generation
\r\nThe data used in this competition is a sample of Grockit students (from the past three years) answering questions to prepare for the sat, gmat, or act. The test/training split is derived by finding users who answered at least 6 questions, taking one of\r\n their answers (uniformly random, from their 6th question to their last), and inserting it into the test set. Any later answers by this user are removed, and any earlier answers are included in the training set. All answers from users not in the test set\r\n are also used for the training set (as they may be useful in estimating question parameters or baseline ability distributions).
\r\nThe test data distribution is thus different from training data in ways that may be significant. First, it does not include 'timeout' or 'skipped' outcomes: all test results are from the student actually answering the question. \r\n Second, it is biased towards users with more questions in the training set and biased towards their later answers. Third, it is one entry per user, so the distribution of various aspects of the data (such as correct/incorrect) is over users, not over all\r\n answered questions.
\r\nWe have attempted to provide a reasonable validation split on the training data by taking the previous correct/incorrect answer for each of the students in the test set, for those users who had at least one previous answer. The results are in the additional\r\n files valid_training.csv and valid_test.csv (in the zip/7z file). Participants may find it helpful to compare potential algorithms by training on the valid_training.csv file and computing their performance on the valid_test.csv files. However, there is no\r\n guarantee that this is an optimal validation set.
", "isPublished": false, "hasIsPublished": false, "postTitle": "", "hasPostTitle": false, "mimeType": "", "hasMimeType": false }, { "name": "Prizes", "content": "The prize pool is $5,000 ($3,000 for first, $1,500 for second and $500 for third), with entries judged using\r\nCapped Binomial Deviance.
\r\nTo be eligible for a prize, the contestant must deliver the Prediction Algorithm’s code and documentation for verification within 21 days. Documentation must be written in English and must be written so that individuals trained in computer science can replicate\r\n the winning results. Source code must contain a description of resources required to build and run the method. Conditional winners must be available to provide assistance to the judges verifying their Entries.
", "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 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 2 entries per day.
\r\nYou may select up to 5 final submissions for judging.
\r\nStart Date: 11/18/2011 10:07 PM UTC
\r\nMerger Deadline: None
\r\nEntry Deadline: None
\r\nEnd Date: 2/29/2012 11:59 PM UTC
\r\n\t\r\n", "isPublished": false, "hasIsPublished": false, "postTitle": "", "hasPostTitle": false, "mimeType": "", "hasMimeType": false } ] }