{
  "fetched_at": "2026-10-20T01:12:13Z",
  "source_url": "https://www.kaggle.com/competitions/2024-term1-actl3142-assignment/data",
  "pages": [
    {
      "name": "data-description",
      "content": "On this Kaggle competition page, you are provided with the competition dataset (**NSW_Crash_data_2016_2022_test.csv**) comprises of 10,000 accidents where we only have Information Received Before a Unit is Onsite. This is of the same format with the dataset provided to you in Part 2 of the assignment. You are required to predict the 100 accidents that are most likely to result in a fatality. Additionally, a sample submission file is included to demonstrate the correct format of a submission file. \n\n\n## Files\n*   **NSW_Crash_data_2016_2022_test.csv** - the test set\n*   **sample_submission.csv** - a sample submission file in the correct format\n\n## Columns\nRefer to **Data manual for variable in dataset** pdf on the Moodle page for any information about the columns of the dataset. ",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "Description",
      "content": "The Kaggle Competition is not compulsory for the ACTL3142 Assignment in 2024 Term 1. \n\nIt serves the purpose for you to validate your model on completely unseen dataset. It also allows you to compare your best model to other peers' best model performance. Additionally, you will be granted bonus points if you have demonstrated excellent performance in the Kaggle competition. Further information on bonus points could be found on Moodle or Ed Forum.",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "Evaluation",
      "content": "Submissions are evaluated on [Recall Score](https://scikit-learn.org/stable/modules/generated/sklearn.metrics.recall_score.html) between the predicted target (Fatality) and the observed Fatality.\n\n\n## Submission File\nFor each **Crash_ID** in the test set, you must predict an outcome for the **Fatality** variable (TRUE or FALSE). You are only allowed to predict 138 positive (i.e. TRUE) for Fatality. The file should contain a header and have the following format:\n\n    Crash_ID, Fatality\n    1195765, FALSE\n    1178429, FALSE\n    1253717, FALSE\n    etc.\n\nNote: The submission file should include all 10,000 accidents with only 138 positives for fatality. Fail to do so could result in a lower recall score. Be aware that this is different to the submission file in Moodle.",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "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.\n\n**Team Mergers**\nTeam mergers is not allowed in this Kaggle competition. You are only allowed to make submission for yourself. Please put your full name in your Kaggle account so it could be matched to Moodle.\n\n**Submission Limits**\nYou may submit a maximum of 5 entries per day.\n\n**Competition Timeline**\nCompetition Timeline dates (including Entry Deadline, Final Submission Deadline, Start Date) are reflected on the competition’s [Overview > Timeline](https://www.kaggle.com/competitions/2024-term-1-actl3142-assignment/overview) page.\n\n**Bonus Marks Allocation**\nPlease see Moodle for detailed explanation of the bonus mark.",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "abstract",
      "content": "Welcome to the ACTL 3142 Kaggle competition on predicting fatality in car accidents based on driver characteristics. In this competition, you are invited to submit your predictive models determining the probability of a car accident to result in a fatality. \n\nThe competition dataset (NSW_Crash_data_2016_2022_test.csv) comprises of 10,000 accidents where we only have Information Received Before a Unit is Onsite. From this dataset comprised of 10,000 accidents you have, compose the probability of fatality for each accident. This competition dataset has the same format as the NSW_Crash_data_2016_2022.csv training dataset but doesn’t include the column Fatality nor the Onsite Investigation variables. We know the column Fatality for the dataset and we will release it after the due date of the assignment.\n\n**Goal:** Your task is to predict 138 accidents that are most likely to result in a fatal accident. You goal is to maximise the Recall score of your predictions. Read below in the Evaluation session for further explanation. ",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    }
  ]
}