{
  "fetched_at": "2026-10-19T19:39:38Z",
  "source_url": "https://www.kaggle.com/competitions/bitcoin-crash-prediction/data",
  "pages": [
    {
      "name": "data-description",
      "content": "In this open competition, you'll use time series forecasting to predict the price of Bitcoin between November 1 and 20, 2021.\n\nThe training data includes the COMMODITIES, STOCK, INDEX and CURRENCIES folders containing CSV files with historical asset prices. Assets price are recorded **each day** in **$USD**. The recording of every assets ends on October 31, 2021 (hence we only have access to past covariates).\n\n## Columns\n\nEvery CSV file has :\n*   `Date` - current date\n*   `Open` - the price from the first transaction of a business day\n*   `High` - the highest price reached during the day\n*   `Low` - the lowest price reached during the day\n*   `Close` - the last price anyone paid for a share of that stock during a business day\n*   `Adj Close` - Adjusted close is a stock's closing price that has been adjusted to account for any corporate actions, such as stock splits, dividends, or rights offerings, that may affect the stock price.\n*   `Volume` - the number of shares or contracts traded during the day\n\n*Keep in mind that some assets aren't trade during the weekend !*\n\n## Main Files\n\n*   **BTC-USD_train.csv** - Bitcoin price\n*   **sample_submission.csv** - The file to fill with your Bitcoin price predictions from November 1 to 20, 2021.\n\n## Folders\n\n### COMMODITIES\n\n*   **CORN.csv** - Corn price\n*   **COTTON.csv** - Cotton price\n*   **GOLD.csv** - Gold price\n*   **OIL.csv** - Oil price\n*   **SILVER.csv** - SI:CMX price\n\n### CURRENCIES\n\n*   **BCH-USD.csv** - Bitcoin Cash price\n*   **BNB-USD.csv** - Binance Coin price\n*   **DOGE-USD.csv** - Doge Coin price\n*   **ETH-USD.csv** - Ethereum price\n*   **EUR-USD.csv** - Euro price\n*   **GBP-USD.csv** - Pound sterling price\n*   **JPY-USD.csv** - Japanese Yen  price\n*   **SOL-USD.csv** - Solana price\n\n### INDEX\n\n*   **ASX.csv** - ASX 200 (the top 200 publicly listed companies on the Australian Securities Exchange)\n*   **CAC40.csv** - Benchmark index for the French stock market (the 40 most significant stocks among the 100 largest market caps on the Euronext Paris)\n*   **DAX.csv** - Benchmark index for the German stock market (the 40 major German blue chip companies trading on the Frankfurt Stock Exchange)\n*   **DJIA.csv** - Dow Jones Industrial Average (the 30 prominent companies listed on stock exchanges in the United States)\n*   **HSI.csv** - Hang Seng Index (the 66 largest companies of the Hong Kong stock market)\n*   **IBEX.csv** - IBerian IndEX (the 35 most liquid Spanish stocks traded in the Madrid Stock Exchange General Index)\n*   **NDX.csv** - Nasdaq-100 (101 equity securities issued by 100 of the largest non-financial companies listed on the Nasdaq stock exchange)\n*   **NKD.csv** - Nikkei 225 (the performance of 225 large, publicly owned companies in Japan from a wide array of industry sectors)\n*   **SPX.csv** - Standard and Poor's 500 (the stock performance of 500 of the largest companies listed on stock exchanges in the United States)\n*   **UKX.csv** - Financial Times Stock Exchange 100 Index (the 100 companies listed on the London Stock Exchange with the highest market capitalisation)\n\n### STOCK\n\n*   **AAPL.csv** - Apple stock price\n*   **AMZN.csv** - Amazon stock price\n*   **GOOG.csv** - Google stock price\n*   **META.csv** - Meta (formerly Facebook) stock price\n*   **MSFT.csv** - Microsoft stock price\n*   **NKE.csv** - Nike stock price\n*   **TSLA.csv** - Tesla stock price\n*   **WMT.csv** - Walmart stock price",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "Description",
      "content": "## Goal of the Competition\n\nIn this open competition, you'll use time series forecasting to predict the price of Bitcoin between November 1 and 20, 2021.\n\nThe objective is to evaluate the ability of current Machine Learning models to predict the future price of an asset. To achieve this, you'll have to rely only on technical data, as the database only contains the history of other assets. We will therefore explore the possibility of predicting asset prices through technical analysis only, i.e. without any information from newspapers or Twitter.\n\n\n## Context\n\nThe day of November 16th, 2021, Bitcoin, after a long and seemingly inexorable bull run, began to crash.\n\nThe challenge in predicting the Bitcoin price doesn't lie in forecasting how high the price will rise, but rather in anticipating a shift in trend. People who anticipated this change in trend in November 2021 were able to avoid heavy losses, perhaps even take advantage of this situation that few had expected and profit from it.\n\n## Why this competition exists ?\n\nThis competition is thought as a first approach to try to predict the future value of Bitcoin (and assets in general). It is intended for Machine Learning practitioners who are interested in crypto-currencies and want to experiment freely with an already available dataset and an easy-to-use interface to evaluate their results.\n\n*It should be noted that a machine learning model that performs well in this competition is in no way guaranteed to accurately predict the price of Bitcoin in general. To achieve this, further analysis of the machine learning model would be required.*",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "rules",
      "content": "## No cheating\n\nAs the actual Bitcoin price between November 1 and 20, 2021 is already known, you are not allowed to copy this information and submit it as a prediction file. Therefore, submissions with a score of 0 will be disqualified. \n\n## One account per participant\n\nYou cannot sign up to Kaggle from multiple accounts and therefore you cannot submit from multiple accounts.\n\n## No private sharing outside teams\n\nPrivately sharing code or data outside of teams is not permitted. It's okay to share code if made available to all participants on the forums.\n\n## Team Mergers\n\nTeam mergers are allowed and can be performed by the team leader. In order to merge, the combined team must have a total submission count less than or equal to the maximum allowed as of the Team Merger Deadline. The maximum allowed is the number of submissions per day multiplied by the number of days the competition has been running.\n\n## Team Limits\n\nThe maximum team size is 5.\n\n## Submission Limits\n\nYou may submit a maximum of 5 entries per day.\n\nYou may select up to 2 final submissions for judging.\n\n## Competition Timeline\n\nStart Date : **April 11, 2023**\n\nEnd Date : **August 12, 2023 - 11:59 AM**",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "Evaluation",
      "content": "The evaluation metric for this competition is Root Mean Squared Logarithmic Error.\n\nThe RMSLE is calculated as :\n\n$$ \\sqrt{ \\frac{1}{n} \\sum_{i=1}^n \\left(\\log (1 + \\hat{y}_i) - \\log (1 + y_i)\\right)^2} $$\n\nwhere :\n\n- 𝑛 is the total number of instances,\n- 𝑦̂𝑖 is the predicted value of the target for instance (i),\n- 𝑦𝑖  is the actual value of the target for instance (i), and,\n- log is the natural logarithm.\n\n\n## Submission File\n\nFor each `id` in the test set, you must predict a Bitcoin closing value. The file should contain a header and have the following format:\n\n```\nid,Close\n2602,0.0\n2603,0.0\n2604,0.0\n2605,0.0\n2606,0.0\netc.\n```",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "Frequently Asked Questions",
      "content": "## How do I create and manage a team?\n\nWhen you accept the competition rules, a team will be created for you. You can invite others to your team, accept a merger with another team, and update basic information like team name by going to the Team page.\n\nWe've heard from many Kagglers that teaming up is the best way to learn new skills AND have fun. If you don't have a teammate already, consider asking if anyone wants to team up in the discussion forum.\n\n## What are Notebooks?\n\nKaggle Notebooks is a cloud computational environment that enables reproducible and collaborative analysis. Kernels supports scripts in R and Python, Jupyter Notebooks, and RMarkdown reports. Go to the Notebooks tab to view all of the publicly shared code on this competition. For more on how to use Notebooks to learn data science, visit Kaggle's Learn Courses.\n\n## How do I make a submission?\n\nIn this code competition, your `submission.csv` file must be generated as an output from a Kaggle notebook. To submit from a notebook, you should:\n\n1. \"Commit\" / \"Save & Run\" a notebook that generates a `submission.csv` containing your predictions in the correct format (requirements described above).\n2. Go to the \"Output\" section of the notebook in viewer mode.\n3. The `submission.csv` can then be submitted to the competition via the \"Submit to Competition\" button.\n\nThis is not a code competition with a hidden test set. And there is no private leaderboard. Therefore, your code will not be re-run on a private test set, and the test set provided on the Data page is the full set of observations for which your `submission.csv` must make predictions.",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    }
  ]
}