{
  "fetched_at": "2026-10-20T07:15:25Z",
  "source_url": "https://www.kaggle.com/competitions/big-data-hms-assignment-7-2024/data",
  "pages": [
    {
      "name": "data-description",
      "content": "Here you can find all the data that you need. You will find a .csv file with training data (features and actual finish times), a test-set with just the features (you will need to predict finish times on this dataset and upload your solutions), and a sample that shows you what you solutionfile should look like.\n\nFile descriptions\n\nchallenge_train.csv - the training set\n\nchallenge_predict_set.csv - the test set\n\nExampleSolution.csv - a sample submission file in the correct format\nData fields\n\nid - participant id\n\nCategory - participant category (age group & pro/am)\n\nFinish_Time - actual finish times in seconds\n\nSwim_To_Bike_Transfer - time to transfer from swimming to the bike in seconds\n\nBIKE_5km_split - 5K Bike Split time in seconds\n\nBIKE_37_5km_split - 37.5K Bike Split time in seconds\n\nBike_To_Run_Transfer - time to transfer from bike to running in seconds\n\nRUN_3_5km_split - 3.5K Run Split time in seconds\n\nRUN_4_5km_split - 4.5K Run Split time in seconds\n\nRUN_8_0km_split - 8.0K Run Split time in seconds",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "Description",
      "content": "In this competition you will have to predict finish times for participants last year's Challenge Roth Triathlon. The Challenge Roth is very popular with thousands of participants every year, and multiple world records have been broken here in the past\n\nThe Challenge Roth is a triathlon over Iron Man distance. Meaning participants will have to swim 3.86K, Bike 180.2K and run a marathon at the end. Your task is to predict finish times based on split times. However, you will only get the transfer times, first 2 bike splits and first 3 running splits!\n\nThe challenge is to predict finish times as accurate as possible. Like any data science challenges there will be simple and complex solutions. You are free to use any model you want, and you will still get your grade points if you finish last. But like in the triathlon, you will only get your medal if you actually finish, so make sure to upload your solution before the deadline",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "Evaluation",
      "content": "The evaluation metric for this competition is RMSE . The Root Mean Squared Error (RMSE) tells you something about the accuracy of your predictions. The higher the RMSE, the further your prediction differs from the truth For every athlete in the dataset, submission files should contain two columns: id and predicted. id should be set as the index column of your submission file. and predicted contains the predicted finish times for all athletes in the test set. Make sure your submission has this format, otherwise you will not be able to upload your submission to Kaggle.",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "rules",
      "content": "The rules for this InClass competition:\n\n- You get your 0.5 points if you upload a submission. So before the deadline you just have to make sure you are on the leaderboard.\n\n- Manual labeling of finish times is not allowed.\n\n- You are not allowed to use the finish place column (the original index) as a feature in any of your models. Doing so will probably result in very low and unrealistic RMSE.\n\n- You are allowed to use any prediction algorithm that you like. Feel free to explore\n\n- If you wish to share your code to help others, do so by uploading a Kernel to the Kaggle page so everyone can benefit.\n\n- Team entries are not allowed for this competition.\n\n- Any RMSE of 0.000 is considered unrealistic and therefore submissions with RMSE are very dubious. If you submit a submission that has an RMSE of 0.00 we kindly ask you to remove if from the leaderboard. Did you manage to achieve an RMSE of 0 with only split & transfer times? Good work, upload your code as a Kernel to prove it and you will get your place on the leaderboard back! ;-)\n\n- Enjoy!",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    }
  ]
}