{
  "fetched_at": "2026-10-20T01:27:40Z",
  "source_url": "https://www.kaggle.com/competitions/cmpe-256-f2019-hw1/data",
  "pages": [
    {
      "name": "rules",
      "content": "This is a page where you can include rules that participants must accept before joining. You may wish to include rules like:\n\n - Don't cheat!\n - Apply yourself!\n - Have fun!",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "data-description",
      "content": "<h2>Data Description:</h2>\nThe training dataset consists of 85724 ratings and the test dataset consists of 2154 ratings. We provide you with the training data ratings and the test ratings are held out. The data are provided as text in train.dat and test.dat, which should be processed appropriately. \n\n**train.dat**: Training set (UserID <tab separator> ItemID <tab separator> Rating (Integers 1 to 5) <tab separator> Timestamp (Unix time stamp).\n\n**test.dat**: Testing set (RatingID<coma separator>, UserID <coma separator> ItemID, no rating provided).\n\n**format.dat**: A sample submission with 2154 ratings. (These are random values, and shall be replaced with your predicted ratings in the order of the test.dat file for your submission). \n",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "Description",
      "content": "<h2>Assignment description</h2>\n\nDevelop a Collaborative Filtering system to predict as accurately as possible the user item ratings.\n\n\nCollaborative Filtering (CF) systems measure similarity of users by their item preferences and/or measure similarity of items by the users who like them. For this CF systems extract Item profiles and user profiles and then compute similarity of rows and columns in the Utility Matrix. (In this assignment you are given a number of ratings, from which it is possible to build a utility matrix.) In addition to using various similarity measures for finding the most similar items or users, one can use latent factor models (matrix decomposition) and other hybrid approaches to improve on the training and test data RMSE scores. We encourage you use functions available in spark libraries for similarity computation, SVD decomposition etc. Performing these tasks in parallel on multiple cores is required as the dataset is quite large. \n\nThe goal of this assignment is to allow you to develop collaborative filtering models that can predict the rating of a specific item from a specific user given a history of other ratings.\nTo evaluate the performance of your results we will use the Root-Mean-Squared-Error (RMSE).\n\n<h2>General guidelines</h2>\n1. Valid submissions to this competition on Kaggle (i.e. your predictions) (follow the format.dat file)\n2. Canvas Submission of source code of your solution, your output file, and report (only your final submission):\n* Create a folder called hw1-YourSjsuID.\n* Create a subfolder called src and another called report.\n* Put all the source code (including any scripts used for pre-processing) in the src subfolder. This should be the spark script you ran to obtain the submitted results. \n Your solution.csv file\n* Place a (max) 2-page, single-spaced report in the report subfolder. It should describe the steps you followed for developing your final solution. Be sure to include the following in the report:\n    * Name, SJSU ID, kaggle ID (if other than your name).\n    * Rank and RMSE for your submission (at the time of writing the report).\n    * Data pre-processing steps and other approaches.\n    * A description of the algorithm(s) you used as well as any associated parameters.\n    * Links to sources if you re-used existing code (with a short description on which parts).\n        * Archive your parent folder (.zip or tar.gz) and submit via Canvas to the respective assignment before the deadline.\n\nFailure to follow the above guidelines (missing files, etc.) will cost you points.\n\n<h2>Grading</h2>\nGrading for the Assignment will be split on your implementation (60%), report (20%) and ranking submissions (20%).\n\nThe ranking score will be defined as follows (out of 20%):\n0%: If below the baselines\n10: If in low-35% of leaderboard\n15%: If mid-35% of leaderboard\n20%: If in top-35% of leaderboard\n\n\nExtra credit (1% of final grade) will be awarded to the top-3 performing algorithms. However before assigning the extra credit, the code will be re-run to verify that the submitted solution file corresponds to that generated by your code.",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "Evaluation",
      "content": "The Root Mean Square Error (RMSE) will be used to evaluate the submissions.\n\nFor each (userid, trackid) pair in the testing dataset, predict the rating that user will give to that track. \n\n<p>The file should contain a header and have the following format:</p>\n<pre>RecommendationId, Rating<br />1, 2.6<br /><span style=\"font-size: 14px; line-height: 1.4em;\">etc.</span></pre>",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    }
  ]
}