{
  "fetched_at": "2026-10-19T08:47:43Z",
  "source_url": "https://www.kaggle.com/competitions/crypto-bull-prediction-challenge/data",
  "pages": [
    {
      "name": "data-description",
      "content": "## Files\n\n*   **train.csv** - The train dataset.\n*   **test.csv** - The test dataset.\n*   **sample_submission.csv** - A sample submission file in the correct format.\n\n## Columns in train.csv\n\n*   `date` - Date and time in the format 'YYYY-MM-DD HH:MM:SS'.\n*   `symbol` - The symbol or name of the cryptocurrency.\n*   `open` - The opening price of the cryptocurrency for the hour.\n*   `high` - The highest price of the cryptocurrency for the hour.\n*   `low` - The lowest price of the cryptocurrency for the hour.\n*   `close` - The closing price of the cryptocurrency for the hour.\n*   `volume` - The trading volume for the hour.\n*   `trades` - Number of trades during the hour.\n*   `close_unixtime` - Closing time in UNIX format.\n*   `target` - The predicted value indicating an increase (1) or decrease (0) in the cryptocurrency price.\n\n## Columns in test.csv\n\n*   `date` - Date and time in the format 'YYYY-MM-DD HH:MM:SS'.\n*   `symbol` - The symbol or name of the cryptocurrency.\n*   `open` - The opening price of the cryptocurrency for the hour.\n*   `high` - The highest price of the cryptocurrency for the hour.\n*   `low` - The lowest price of the cryptocurrency for the hour.\n*   `close` - The closing price of the cryptocurrency for the hour.\n*   `volume` - The trading volume for the hour.\n*   `trades` - Number of trades during the hour.\n*   `close_unixtime` - Closing time in UNIX format.\n*   `id` - Unique identifier for the record.\n\n## Columns in sample_submission.csv\n\n*   `id` - Unique identifier for the record.\n*   `target` - The predicted value indicating an increase (1) or decrease (0) in the cryptocurrency price.\n\n\n",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "Evaluation",
      "content": "The evaluation section describes how submissions will be scored and how participants should format their submissions.\n\n---\n\nSubmissions are evaluated on [area under the ROC curve](http://en.wikipedia.org/wiki/Receiver_operating_characteristic) between the predicted probability and the observed target.\n\nTarget calculated as follows:\n```python\ndata[price].pct_change(horizon).shift(-horizon).fillna(0) > threshold\n```\nwhere `price`, `horizon` and `threshold` are parameters set constant for this competition.\n\n## Submission File\nFor each ID in the test set, you must predict a probability for the TARGET variable. The file should contain a header and have the following format:\n\n    id,target\n    2,0\n    5,0\n    6,0\n    etc.",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "rules",
      "content": "- Don't cheat!\n- Apply yourself!\n- Have fun!",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "abstract",
      "content": "Welcome to the \"Crypto Bull Prediction Challenge\"!\n\nCryptocurrencies have taken the world by storm, and with their increasing popularity, the volatility and unpredictability of their prices have also soared. Traders, investors, and enthusiasts are always on the lookout for patterns, insights, and predictions. This competition challenges you to harness the power of machine learning to forecast cryptocurrency trends. Can you predict the next bearish trend for a given cryptocurrency?\n\n> **Important Note on Time Series Data:**\n>\n>\n> Time series data has a natural temporal ordering, which makes it different from other types of data. When generating features or using libraries, it's paramount to ensure you don't inadvertently introduce future information into the past, a phenomenon known as \"data leakage\". Data leakage can result in overly optimistic performance metrics during model evaluation and can be a critical mistake in real-world scenarios.\n>\n> Always be meticulous about the indicators you incorporate and the libraries you leverage. Data leakage is a grave oversight in time series analysis and, if detected, will lead to disqualification from the competition.\n>\n> For a deeper understanding of data leakage in time series, refer to these articles:\n> - [How (not) to use Machine Learning for time series forecasting: Avoiding the pitfalls](https://towardsdatascience.com/how-not-to-use-machine-learning-for-time-series-forecasting-avoiding-the-pitfalls-19f9d7adf424)\n> - [Understanding Data Leakage in Machine Learning](https://machinelearningmastery.com/data-leakage-machine-learning/)\n",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    }
  ]
}