{
  "fetched_at": "2026-10-19T11:32:47Z",
  "source_url": "https://www.kaggle.com/competitions/applications-of-deep-learning-wustlfall-2022/data",
  "pages": [
    {
      "name": "data-description",
      "content": "## Files\n\n*   **sample_submit.csv** - Sample submission file.\n*   **sales_test.csv** - The test/submit data for the competition.\n*   **sales_train.csv** - The training data (tabular) for the competition. Sales over time.\n*   **items.csv** - The 100 items for sale, includes textual NLP data.\n*   **resturants.csv** - The restaurants that sell the items.\n*   **./cam/*.jpg** - Daily images from a webcam placed near the restaurants.\n\n\n## Columns\n\nItems: \n\n*   `id` - Unique identifier for this item. The item ID.\n*   `store_id` - The restaurant that sells this item. Restaurant ID.\n*   `name` - The name of this item. NLP techniques are likely helpful with this item.\n*   `kcal` - How many calories is this item.\n*   `cost` - The base cost for this item.\n\nRestaurants:\n\n*   `id` - Unique identifier for this restaurant. The Restaurant ID.\n*   `name` - The name of the restaurant.\n\nSales (training)\n*   `date` - The date that this sale occured.\n*   `item_id` - The item that was sold. The item ID.\n*   `price` - The price that this item was sold for on this day.\n*   `item_count` - Unique identifier for this item. The target (y).\n\nSubmission File:\n*   `id` - Unique identifier for this prediction, aligns to the same `id` field from the test data.\n*   `item_count` - The prediction (y-hat).\n\n## Tabular Data\n\nThe tabular data for this competition exists in the sales, items and restaurants CSV files.\n\n## Image Data\n\nThere is a webcam that records an image a day in front of the restaurants. You can see sample images here. Notice the size of the crowd on the street and beach. The filenames correspond to the date the image was taken.\n\n![Beach CAM 1](https://data.heatonresearch.com/images/wustl/kaggle/demand_forecast/2019_01_01.jpg)\n\n![Beach CAM 2](https://data.heatonresearch.com/images/wustl/kaggle/demand_forecast/2019_01_02.jpg)\n\n![Beach CAM 3](https://data.heatonresearch.com/images/wustl/kaggle/demand_forecast/2019_01_06.jpg)\n\n## Textual Data\n\nThere is also textual data in the items files. This data might also be useful.\n\n\n\n\n\n\n\n\n\n",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "Description",
      "content": "This competition is provided as a way to explore different time series techniques on a relatively simple and clean dataset. Your task is to forecast demand for four beach front restaurants with a variety of items for sale. \n\nYou are given 2.75 years of store-item sales data, and asked to predict 3 months of sales for 10 different items at 5 different restaurants. Your data set contains both structured and unstructured elements.\n\nWhat is the best way to deal with seasonality? Should items be modeled separately, or can they be combined? Should you choose deep learning or ARIMA? Can either beat XGBoost?\n\nThis competition allows you to explore different models and improve your skills in forecasting.\n\n![About the Data](https://data.heatonresearch.com/images/wustl/kaggle/demand_forecast/introduce_data.png)\n\n## Similar Kaggles\n\n* [Store Item Demand Forecasting Challenge](https://www.kaggle.com/c/demand-forecasting-kernels-only)\n\n# Where the data came from\nThis data was created using a multi-agent simulation.\n\n* Location: Ft. Lauderdale, FL, USA.\n* Data from Jan 1, 2019 to Dec 31, 2021\n* Dates only specify seasonality\n* No black swan events: no pandemics, wars, market conditions, etc.\nHolidays matter.\n* Data set contains \"trends\" and multiple seasonalities.",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "Evaluation",
      "content": "# RMSE Evaluation\n\nYou must calculate the items sold for all 100 item times for all of the days in the third quarter of 2021. The difference between your estimate of distance and the actual distance will result in a [root mean square](https://en.wikipedia.org/wiki/Root-mean-square_deviation) (RMSE) error, which forms the basis of your evaluation and leaderboard rank.\n\n## Submission Format\n\nThe file should contain a header and have the following format:\n```\nid,item_count\n0,6.2\n1,6.2\n2,6.2\n3,6.2\n4,6.2\n```",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "rules",
      "content": "Teams of up to 5 students are allowed.",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    }
  ]
}