{
  "fetched_at": "2026-10-20T07:48:45Z",
  "source_url": "https://www.kaggle.com/competitions/epsilon-sales-forecasting-time-series-prediction/data",
  "pages": [
    {
      "name": "data-description",
      "content": "Model Dataset Train.csv - the training set\nModel Dataset Test.csv - the test set\nsample_submission.csv - a sample submission file in the correct format",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "Description",
      "content": "In this “getting started” competition, you’ll use time-series to predict the demand forecasting on weekly basis.\nSpecifically, you'll build a model that more accurately predicts the weekly sales . You'll practice your machine learning skills with an approachable training dataset of price of goods, crude price, us govt incentive and all Covid related information.\n\nObject of this problem is to predict the demand forecasting for 12 weeks based upon the previous data and sale.\n\nDataset contains rows (~140) and around 160 features.\n\nChallenges you might face\n\n1 – Feature selection and Feature engineering – small subset of variables to pick (~15-30) from the entire huge list of variables, not all variables will be relevant.\n\n2 – Hyperparameter tuning – Model will be sensitive to Hyperparams (learning rate, epochs, num of LSTM cells, epsilon, rho, beta etc) – what would be a right combination to get minimum error",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "Evaluation",
      "content": "The evaluation metric for this competition is Mean Absolute Error.\n\nMean Absolute Error = (1/n) * ∑|yi – xi|\n\nΣ: Greek symbol for summation\nyi: Actual value for the ith observation\nxi: Calculated value for the ith observation\nn: Total number of observations\n\nSubmission File\nFor each id in the test set, you must predict a value for the sales variable. The file should contain a header and have the following format:\n\nWEEKSTARTDATE Sample Values\n3/15/2020 0.00\n3/22/2020 0.00\n3/29/2020 0.00\n4/5/2020 0.00\n4/12/2020 0.00\n4/19/2020 0.00\n4/26/2020 0.00\n5/3/2020 0.00\n5/10/2020 0.00",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "rules",
      "content": "This is a page where you can include rules that participants must accept before joining. You may wish to include rules like:\n\n - Don't cheat!\n - Apply yourself!\n - Have fun!\n",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    }
  ]
}