{
  "fetched_at": "2026-10-19T21:44:30Z",
  "source_url": "https://www.kaggle.com/competitions/advanced-horse-speed-forecast-time-climate/data",
  "pages": [
    {
      "name": "data-description",
      "content": "\n\n\nFiles\ntrain_final.csv - This is the training dataset. It contains historical data on horse races, including the date, race time, weather conditions, and the actual horse speed.\n  \ntest_final.csv - This is the test dataset. It provides information on the races' date, race time, and weather conditions but omits the actual horse speed. Your task is to predict the horse speed for these races.\n\nsample_submission_final.csv - A sample submission file in the correct format, demonstrating how to format your predictions.\n\nColumns\n\nDate - The date on which the race took place.\n  \nRace_Time - The specific time the race started.\n  \nWeather - Describes the weather condition during the race. It can be 'Sunny', 'Cloudy', 'Rainy', or 'Stormy'.\n  \nHorse_Speed (only in training data) - Represents the speed of the horse during the race.\n  \nID (specifically for submission) - A combination of the date, race time, and an index, used to uniquely identify each race in the test set.\n\nObjective\n\nYour main objective is to predict the Horse Speed for each race in the test set based on the given conditions.\n\n**Important**: Please use the latest version of the \"sandbox_grand_final.csv\" file for sandbox submissions. Older versions are deprecated.\n\n\n\n",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "Description",
      "content": "The world of horse racing is dynamic and ever-changing, with countless factors influencing the outcome of a race. In this competition, we delve deep into the nuances of horse speeds, presenting a challenge that requires participants to predict the speed of a horse during a race.\n\nThe provided dataset encapsulates over 100,000 races, each with its unique set of conditions. The primary variables include the date of the race, the time the race took place, and the weather condition during the race. The challenge is to use this data to predict the speed of a horse under different conditions.\n\n\nDataset\nThe dataset is divided into training and testing sets. The training set consists of 100,000 rows, each row representing a unique race. The columns in the dataset are:\n\nDate: The date the race took place.\n\nRace_Time: The time of the day the race occurred.\n\nWeather: The weather condition during the race. It has categories such as 'Sunny', 'Cloudy', 'Rainy', etc.\n\nHorse_Speed: The speed of the horse during the race. This is the target variable for the training set.\nThe testing set follows a similar structure but lacks the Horse_Speed column. \n\n\nParticipants are expected to predict this missing column using the given conditions.\n\nEvaluation\n\n\nThe Mean Absolute Error (MAE) is used to evaluate submissions in this competition. It measures the average magnitude of errors between predicted and actual horse speeds. It's calculated as:\n\nMAE = (1/n) * SUM(|y_i - yhat_i|)\n\nWhere:\n\nn is the number of observations.\ny_i is the actual horse speed for the ith race.\nyhat_i is the predicted horse speed for the ith race.\nAim to minimize the MAE for a higher leaderboard position. The closer the MAE is to zero, the better the predictions\n\n\n\n\n\n​\n\nChallenge\nThe intricate patterns and relationships between the variables in this dataset make it an elite-level challenge. While the variables might seem simple at first glance, their combined interactions create a complex landscape for prediction. This competition is designed to push the boundaries of traditional machine learning and encourage innovative approaches.\n\nAre you ready to take on the challenge and gallop your way to victory?\n\n\n\n\n",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "Evaluation",
      "content": "\n\nSubmissions are evaluated on the Mean Absolute Error (MAE) between the predicted horse speed and the actual horse speed. MAE measures the average magnitude of errors between predicted and actual horse speeds. It's calculated as:\n\nMAE = (1/n) * SUM(absolute(y_i - yhat_i))\n\nWhere:\n- n is the number of observations.\n- y_i is the actual horse speed for the ith race.\n- yhat_i is the predicted horse speed for the ith race.\n\nParticipants should aim to minimize the MAE for a higher leaderboard position. The closer the MAE is to zero, the better the predictions.\n\n## Submission File\nFor each ID in the test set, participants must predict the horse speed. The file should contain a header and have the following format:\n\n    ID,Horse_Speed\n    2023-01-01_13:00:00,15.5\n    2023-01-01_13:01:00,16.2\n    2023-01-01_13:02:00,15.8\n    etc.\n\nUse the provided sample submission file as a reference for the expected format.\n\n\n\n\n\n\n\n",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "rules",
      "content": "\n\n - Don't cheat!\n - Apply yourself!\n - Have fun!\n- Also use discussion and other features. We can all learn from them\n\nPlease note:\nThis dataset has been artificially generated and is intended solely for educational and competition purposes. It should not be utilized in actual research or considered as a substitute for real-world sampling.",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "abstract",
      "content": "Welcome to the \"Elite Horse Speed Prediction Challenge\"!\n\nIn this competition, participants are tasked with predicting the speed of horses under varying conditions. Drawing from a rich dataset of over 100,000 races, competitors will need to consider factors such as weather and race time to make their predictions.\n\nHarnessing the power of machine learning and neural networks, this challenge offers an intricate problem that tests the mettle of both seasoned data scientists and enthusiastic newcomers. With intricate patterns and a myriad of influencing factors, it's a race to the top of the leaderboard!\n\nGoal:\nYour objective is to build a model that accurately predicts a horse's speed based on given conditions, pushing the boundaries of predictive analytics. Good luck and may the best model win!",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    }
  ]
}