{
  "fetched_at": "2026-10-19T13:29:27Z",
  "source_url": "https://www.kaggle.com/competitions/classificationcompetition2024/data",
  "pages": [
    {
      "name": "data-description",
      "content": "You can use 'IMDb names.csv' dataset from this [link](https://www.kaggle.com/stefanoleone992/imdb-extensive-dataset?select=IMDb+movies.csv).",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "Description",
      "content": "## Predicting the popularity of IMDb movies\nIn this competition, you will have to predict the popularity of IMDb movies by analyzing the data in the proposed dataset. Thus, based on what you learned at the sessions, you'll need to create a model that estimates whether a movie will become popular or not. \n\n\n## Rules\n- The code must be written in Python. \n- You can use any classifier models that are implemented in Python.\n- You will only upload the predictions.csv prediction file.\n- You are not allowed to use features directly related to the evaluation of films, such as ratings/scores of movies, number of votes, or reviews (characteristics of the film that are not known when it appeared on the platform).\n- Have fun!\n\n\n## Final evaluation\nThe participant with the highest Accuracy will win the competition.",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "Evaluation",
      "content": "**Evaluation method**\nTo evaluate the results, you will send only one .csv file each time, in the format below. Additionally, during the competition, you will be able to send a maximum of 2 solutions per day.\n\nIn the leaderboard, you will see the ranking based on 40% of the final evaluation dataset. The score for the other 60% of the data set will be hidden and shown after the competition ends.\n\nIn the end, you will be able to choose two solutions to be evaluated on the final data set.\n\n\n**Submission Format**\nFor each movie in the dataset, the submission file must contain two columns: movie_id and popularity.\n\nThe uploaded file must be saved with the .csv extension in the following format:\n\n<pre>title_index, popularity\n0, popular\n1, unpopular\n2, popular\n</pre>\n\n**Evaluation metrics**\n\nFor evaluation will be used the [\"Classification accuracy\"](https://en.wikipedia.org/wiki/Accuracy_and_precision) metric.\n\nThe classification accuracy defines the number of correctly classified examples divided by the total number of examples in the dataset.",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "rules",
      "content": "\n- The code must be written in Python.\n- You can use any classifier models that are implemented in Python.\n- You will only upload the predictions.csv prediction file.\n- You are not allowed to use features directly related to the evaluation of films, such as ratings/scores of movies, number of votes, or reviews (characteristics of the film that are not known when it appeared on the platform).\n- You can use features from data sets uploaded to OneFile to drive models.\n- Have fun!",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    }
  ]
}