{
  "fetched_at": "2026-10-20T05:31:35Z",
  "source_url": "https://www.kaggle.com/competitions/dss-615/data",
  "pages": [
    {
      "name": "rules",
      "content": "## Submission ##\nYou must rank the importance of affiliations (i.e. institutions) based on predicting how many of their papers will be accepted. You submission will be scored based on the order of the affiliations. Predicting how many papers will be accepted will inherently rank the affiliations. Your submission file should look like:\n\n\n    rank, affiliation_id\n    1, 79533B41\n    2, 7E0706FD\n    3, 800562AD\n    4, 7F0793AC\n    5, 034047C2 \n\n## Reproducibility \nThe script that produces your submission must reproducible. That is, you must have an end to end solution.  \n\n## Teams ##\nYou may work on teams of 1 to 5 people.",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "data-description",
      "content": "The Microsoft Academic Graph is a large and heterogeneous graph containing scientific publication records, citation relationships between publications, as well as authors, institutions, journal and conference \"venues,\" and fields of study. This data is available as a set of tab separated value files.\n\n\nData Sets\n=========\nData from 2011, 2012, 2013, and 2014 for conferences (e.g. FSE, KDD, ICML, etc.) can be found in these files. \n\nConference information (name and year) is inside of **Papers.tsv** while the relationship between papers and affiliations is inside of **PapersAuthorsAffiliations.tsv**. \n\n\nPapers (Papers.tsv)\n--------------------\n- paper_id\n- title\n- publish_year\n- conference_id\n- conference_abbrv\n\nAffiliations (Affiliations.tsv)\n------------\n- affiliation_id\n- name\n\nPaper Author Affiliations (PapersAuthorsAffiliations.tsv)\n-----------------------------\n- paper_id\n- author_id\n- affiliation_id\nThere are extra columns of data in this data set that are pretty messy, you may use them if you wish\n",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "Description",
      "content": "DSS 615: KDD Cup 2016\n===================\nThis in-class prediction competition is modeled after [KDD Cup 2016][1].\n*Whose papers are accepted the most: towards measuring the impact of research institutions*\n\nIn this challenge, you are asked to rank affiliations (i.e. institutions) based on how much they contribute to a field of study (e.g. machine learning, mobile computing).\n\nThe prediction task involves predicting *affiliation rankings* based on the number of research papers that will be accepted to a conference.\n\nAffiliation Rankings\n-----------------------\nWe use the following simple policy to determine the Affiliation Ranking:\n\n1. Each accepted paper has an equal vote (i.e., they are equally important).\n\n2. Each author has an equal contribution to a paper.\n\n3. If an author has multiple affiliations, each affiliation also contributes equally.\n\nSuppose there is a paper which has three authors \"author1\", \"author2\" and \"author3\", who belong to different affiliations \"affiliation1\", \"affiliation2\" and \"affiliation3\", respectively. Then in this case, each affiliation will receive 1/3 vote for its score.\n\nSuppose another paper has two authors \"author1\" (belongs to \"affiliation1\") and \"author4\" (belongs to both \"affiliation3\" and \"affiliation4\". In this case, \"affiliation1\" will receive the score 1/2, while \"affiliation3\" and \"affiliation4\" both receive the score 1/4.\n\nBy aggregating the scores from the above two papers, the final affiliation ranking scores are:\n\n\"affiliation1\" = 1/3 + 1/2 = 0.8333\n\"affiliation3\" = 1/3 + 1/4 = 0.5833\n\"affiliation2\" = 1/3 = 0.3333\n\"affiliation4\" = 1/4 = 0.2500\n\n\n  [1]: https://kddcup2016.azurewebsites.net/",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "Evaluation",
      "content": "## Rounds ##\nWe will start by focusing on predicting for the International Conference on Machine Learning (ICML).\n\nRound 1: Predict ranks for **ICML**\n\n## Objective ## \nBased on the data provided, rank the affiliations based on their *affiliation ranking*.\n\n## Submission ##\nYour submission will be scored based on the order of the affiliations. You only need to rank the affiliations that will participate in **ICML**. Your submission file should look like:\n\n    rank, affiliation_id\n    1, 79533B41\n    2, 7E0706FD\n    3, 800562AD\n    4, 7F0793AC\n    5, 034047C2 \n\nTeams will be evaluated using the same measures used in [KDD Cup 2016][1]. \n\n\n\n  [1]: https://kddcup2016.azurewebsites.net/Rules",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    }
  ]
}