{
  "fetched_at": "2026-10-19T22:45:32Z",
  "source_url": "https://www.kaggle.com/competitions/bia01-univariate-time-series-regression/data",
  "pages": [
    {
      "name": "data-description",
      "content": "## 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## Columns\n\n*   `timestamp` - Time stamp such as 2021-08-02 09:50:00.\n*   `x` - independent variable.\n*   `y` - dependent variable, i.e., label to predict from x.",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "Description",
      "content": "The challenge is to predict time series (y) from a very similar univariate time series (x) without using the identify function (y=x). There are ~73,000 timestamps of training with one measurement every 5 minutes.\nThe following image shows a subsample of the training time series:\n\n![](https://www.googleapis.com/download/storage/v1/b/kaggle-user-content/o/inbox%2F1150148%2Ffa517edca69b408f4fff1f703aa16b90%2Fnewplot.png?generation=1683915723349979&alt=media)",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "Evaluation",
      "content": "Submissions will be evaluated according to Pearson correlation coefficient in a testing set.",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "rules",
      "content": "Submit your own solution. If you improve the baseline, then contact the organizer for your prize.",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    }
  ]
}