{
  "fetched_at": "2026-10-19T16:57:48Z",
  "source_url": "https://www.kaggle.com/competitions/bdaio-2024-the-clothing-sale/data",
  "pages": [
    {
      "name": "data-description",
      "content": "The dataset includes 10,000 training examples and 2000 test examples. Each example is a 28x28 grayscale image associated with one of 10 class labels. \n\nEach image in the dataset measures 28 pixels in height and 28 pixels in width, resulting in a total of 784 pixels. Each pixel has a value between 0 and 255, indicating its lightness or darkness (higher values mean darker pixels). The dataset contains 786 columns: the first column contains the ID, the second column contains the class labels, and the remaining columns contain the pixel values.\n\n**Labels**\nEach example in the training and test datasets is assigned one of the following labels:\n\n- 0 T-shirt/top\n- 1 Trouser\n- 2 Pullover\n- 3 Dress\n- 4 Coat\n- 5 Sandal\n- 6 Shirt\n- 7 Sneaker\n- 8 Bag\n- 9 Ankle boot\n\n## Files\n\n*   **train.csv** - the training set\n*   **test.csv** - the test set\n*   **sample_submission.csv** - a sample submission file in the correct format\n\n",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "Description",
      "content": "The challenge you face is to develop a machine learning model that can analyze these clothing images and accurately classify them into their corresponding categories. The dataset provides labels for each image, with specific categories for different clothing types. Your model's mission is to learn the key visual features that differentiate these categories, ultimately transforming a stream of pixels into a clear understanding of the type depicted.\n",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "Evaluation",
      "content": "Submissions are evaluated based on the `accuracy` ([https://developers.google.com/machine-learning/crash-course/classification/accuracy](url)) of their predicted labels compared to the true target labels.\n\n\n## Submission File\nFor each ID in the test set, you must predict a label for the TARGET variable. The file should contain a header and have the following format:\n\n    ID,label\n    2,0\n    5,0\n    6,0\n    etc.",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "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 - Submit before the time ends\n",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "abstract",
      "content": "Imagine you're a data scientist working for a booming online clothing store. Their virtual shelves overflow with countless styles, from classic t-shirts to trendy gowns. However, keeping track of inventory and categorizing new arrivals is a time-consuming task. The current system relies on manual tagging by human workers, but this approach is slow and prone to errors.\nSo, this is where you need to step in!\n",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    }
  ]
}