{
  "fetched_at": "2026-10-19T19:17:15Z",
  "source_url": "https://www.kaggle.com/competitions/cse2525-datamining/data",
  "pages": [
    {
      "name": "rules",
      "content": "## One account per participant\nYou cannot sign up to Kaggle from multiple accounts and therefore you cannot submit from multiple accounts.\n\n## No private sharing\nPrivately sharing code or data is not permitted. It's okay to share code if made available to all participants on the forums.\n\n## Mergers\nMerging is not allowed in this competition.\n\n## Team Limits\nThe challenge is done on individual basis, so each team exists out of 1 member.\n\n## Submission Limits\nYou may submit a maximum of 15 entries per day.\nYou may select up to 1 final submissions for judging.\n\n## Competition Timeline\nStart Date: March 4th\n\nMerger Deadline: None\n\nEntry Deadline: None\n\nEnd Date: April 10th",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "data-description",
      "content": "**Users.csv:** Information about the users This file contains four columns: (1) a column indicating the index of the user; (2) a column indicating whether the user is male or female; (3) a column indicating the age of the users (if known); and (4) a column containing a number that indicates the profession of the user.\n\n**Movies.csv:** Information about the movies This file contains three columns: (1) a column indicating the index of the movie; (2) a column containing the year the movie was released; and (3) a column containing the title of the movie.\n\n**Ratings.csv:** User-movie ratings This file contains three columns: (1) a column indicating the index of the user who gave the rating; (2) a column indicating the index of the movie that was rated; and (3) a column containing the rating that the user gave to the movie on a scale from 1 to 5.\n\n**Predictions.csv:** List of user-movie ratings that needs to be predicted The file contains two columns: (1) a column indicating the index of the user who gave the rating and (2) a column indicating the index of the movie that was rated. For these user-movie combinations, your algorithm needs to predict the ratings. These predicted ratings need to be written into the submission.csv file.\n\n**Submission.csv:** Example of a submission file The file that you need to write contains two columns: (1) a column indicating the corresponding row in predictions.csv ranging from 1 to 90,019 and (2) a column indicating the predicted ratings. Note that this file uses a comma as column separator (all other files use a semi-colon instead); this is the Kaggle default.",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "Description",
      "content": "The goal of this project is to develop a recommendation algorithm for movies.\nThe data for this project comprises 910,190 ratings (on a 1 to 5 scale) that were given by 6,040 users to 3,706 movies. Next to the ratings, the data contains some information on the users (gender, age, and profession) and information on the movies (title and year of release). You have to develop an algorithm that, based on this data, predicts as good as possible what rating a particular user will give to a particular movie.\n\nUse your @tudelft.nl email address to make an account on kaggle.com.\n\nYou can develop your algorithms in any programming language that you like. For your convenience, we provide Python-code that reads in all data, runs an extremely simple prediction algorithm (namely, predict random ratings), and writes the results into a submission file.",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "Evaluation",
      "content": "# Algorithm evaluation\nTo be able to gauge how well your algorithm works, we have held out a total of 90,019 user-movie ratings. You are supposed to make predictions for these ratings; your predictions will be compared with the true user-movie ratings. To this end, we will measure the root mean squared error (RMSE) of your algorithm.\n\nWhile developing your algorithms, you can measure their RMSE by writing your predictions to a CSV-file and uploading the resulting CSV-file to the Kaggle-in Class website. The website computes the RMSE of your algorithm on a random subset of the 90,019 held-out ratings, and puts your result on the public leaderboard. This allows you to compare your progress with that of other students.\n\nThe final score of your algorithm will be computed after the end of the competition based on the predicted ratings that were not used to compute the score on the leaderboard. This procedure is chosen because it ensures that final scores are not the result of overfitting.",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    }
  ]
}