{
  "fetched_at": "2026-10-19T07:20:22Z",
  "source_url": "https://www.kaggle.com/competitions/ext-market/data",
  "pages": [
    {
      "name": "data-description",
      "content": "## Goals\n\nIn this classic classification problem, your goal is to leverage historical data and various indicators to develop models that can accurately forecast the movement of stock prices. Your task is to predict whether the stock price will experience a decrease (0), increase (1) or remain relatively stable (2) based on the given inputs.\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## Imbalance of the dataset\n\nThe given dataset for this competition is characterized by a significant class imbalance. This means that the distribution of the target variable, which represents the movement of stock prices, is highly skewed towards one or a few classes, while other classes have relatively fewer instances. It is important to be aware of this imbalance when developing your models and evaluating their performance. Consider applying appropriate techniques such as class weighting, oversampling, or undersampling to address this challenge and ensure that your models are capable of effectively capturing patterns across all classes.\n\n## Columns\n\n*   `result` - defines this way:\n - 0 - short: price of the stock goes down more than 2 percents AND does not go up more than 1 percent;\n - 1 - long: price of the stock goes up more than 2 percents AND does not go down more than 1 percent;\n - 2 - hold: price does not match conditions above;\n\n#### Categorical Columns\n\n*   `RSI_signal`\n*   `Stoch_O_signal`\n*   `ichimoku_c_signal`\n*   `fibonacci_signal`\n*   `Bollinger_signal`\n*   `exchange`\n\n#### Numeric Columns\n\nBasically they are all other columns in dataset. But I need to say a few special words about columns below:\n\n*   `ichimoku_c_conversion_line`\n*   `ichimoku_c_base_line`\n*   `ichimoku_c_leading_span_a`\n*   `ichimoku_c_leading_span_b`\n*   `pivot_support_1`\n*   `pivot_resistance_1`\n*   `pivot_support_2`\n*   `pivot_resistance_2`\n*   `pivot_support_3`\n*   `pivot_resistance_3`\n\nThe mentioned indicators represent various points of interest in price movement analysis. These indicators help traders and analysts identify potential areas of price reversals, support, and resistance, enabling them to make more informed decisions in their trading strategies.",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "Description",
      "content": "Welcome to the \"Predicting Stock Market Price Movement\" competition! \n\nIn this challenge, you will tackle the exciting task of predicting the movement of stock market prices using an **extremely imbalanced dataset.**\n\nThe stock market is known for its dynamic and unpredictable nature, making accurate predictions a valuable skill. However, the **imbalanced** nature of this dataset presents an additional challenge, as the occurrence of price movements is heavily skewed towards one class. This competition aims to push the boundaries of predictive modeling by addressing this real-world scenario.\n\nYou will be provided with a comprehensive dataset containing historical price and market indicators for various stocks. The dataset encompasses both bullish and bearish movements, with a significant imbalance in favor of **one of three classes**. Your goal is to build a robust machine learning model that can effectively identify and predict these movements, demonstrating a strong understanding of class imbalance handling techniques.\n\n**Good luck, and may the best model prevail!**",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "Evaluation",
      "content": "\nThe evaluation metric for this competition is Mean F1-Score.\n\nIf you will write a notebook, please mention F1-Scores for each class.\n\nAlso I want to say that distribution of test set is this:\n\n2    98.987625\n1     0.802046\n0     0.210330\n\n\nI want you to know it, because, from the one hand, main metric of contest is F1-Score and because of it you should correctly predict all classes, and from the other hand, I just want to achieve the highest F1-Score possible, and when you know real-life distribution, you will create more accurate models.",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "rules",
      "content": "Do anything you want to achieve highest F1-score!\n\nIf you will write a notebook, please, mention F1-scores for all classes separately. ",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    }
  ]
}