{
  "fetched_at": "2026-10-20T03:28:13Z",
  "source_url": "https://www.kaggle.com/competitions/cs3244-rossmann-store-sales/data",
  "pages": [
    {
      "name": "rules",
      "content": "\n### Use only the given data files\n\nSince data is subsampled from an original competition you should train only on the given subset of data. You can use weakly supervised techniques however, using unspecified training data from original competition (train or test) is not allowed.\n\n### One account per participant\n\nYou cannot sign up to Kaggle from multiple accounts and therefore you cannot submit from multiple accounts.\n\n### No private sharing outside teams\n\nPrivately sharing code or data outside of teams is not permitted. It's okay to share code if made available to all participants on the forums.\n\n### Team Mergers\n\nTeam mergers are allowed and can be performed by the team leader. In order to merge, the combined team must have a total submission count less than or equal to the maximum allowed as of the merge date. The maximum allowed is the number of submissions per day multiplied by the number of days the competition has been running.\n\n### Team Limits\n\nThere is no maximum team size.\n\n### Submission Limits\n\nYou may submit a maximum of 2 entries per day.\n\nYou may select up to 2 final submissions for judging.\n\nCompetition Timeline\n\nStart Date: 11/10/2017 12:00 AM UTC\n\nMerger Deadline: None\n\nEntry Deadline: None\n\nEnd Date: 7/11/2017 11:59 PM UTC\n\nGrading criteria is common to both assignments. We replicate it here for your convenience (For any potential conflicts with the announcement on IVLE, please base the version on IVLE) :\n\n40% on Documentation, which consists of:\n20% on the documentation itself: formatting, clearness, comprehensiveness of your README, as well as how well your team complies with the competition rules. \n20% on the creativity, insight or depth of your solution. \n60% on Relative Performance:\n10% on Training data performance (as reported by you)\n25% on Given testing performance (as reported by Kaggle)\n25% on Held-out testing performance (not available for testing against in Kaggle, will be compiled by our TA group.\nTwo important details about the deliverables:\n\n1) README.pdf. Your README (in .pdf) needs to contain a short 1-3 page report detailing how your team tackled the task, inclusive of documenting any data analysis you performed on the data, normalization, models tried, and any post analysis that you did. In addition to the report, you need to also describe the files that are submitted, include your statement of independent work (or suggest alternative evaluation criteria), and a section of the references you used in your project.\n\n2) Held out testing set. Kaggle makes both the training and testing data available for you to download. Since both problems' full datasets are publicly available, you could recover the labels for the test sets that we provide you, but this regards as cheating. Therefore it is not allowed and all teams should not attempt to use the original public datasets to reconstruct the testing data that is hosted on Kaggle. Such cheating defeats the purpose for the assignment, and your team would be better off investing effort in learning how to apply ML appropriately instead of wasting time to circumvent our efforts to give you a genuine learning problem. Offending teams will be severely prosecuted.\n\n\nWe will also construct new data on our own which we do not provision to Kaggle (held-out testing data), which is given an equal weight in the grading.\n\nWe will be asking you to demonstrate your team's learner on new instances within X days after Homework #3's submission deadline, to establish held-out testing performance. These dates and the workflow process details will be announced later.",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "data-description",
      "content": "You are provided with historical sales data for 1,115 Rossmann stores. The task is to forecast the \"Sales\" column for the test set. Note that some stores in the dataset were temporarily closed for refurbishment.\n\n**Files**\n\ntrain.csv - historical data including Sales\n\ntest.csv - historical data excluding Sales\n\nsample_submission.csv - a sample submission file in the correct format\n\nstore.csv - supplemental information about the stores\n\n\n**Data fields**\n\nMost of the fields are self-explanatory. The following are descriptions for those that aren't.\n\n\nId - an Id that represents a (Store, Date) duple within the test set\n\nStore - a unique Id for each store\n\nSales - the turnover for any given day (this is what you are predicting)\n\nCustomers - the number of customers on a given day\n\nOpen - an indicator for whether the store was open: 0 = closed, 1 = open\n\nStateHoliday - indicates a state holiday. Normally all stores, with few exceptions, are closed on state holidays. Note that all schools are closed on public holidays and weekends. a = public holiday, b = Easter holiday, c = Christmas, 0 = None\n\nSchoolHoliday - indicates if the (Store, Date) was affected by the closure of public schools\n\nStoreType - differentiates between 4 different store models: a, b, c, d\n\nAssortment - describes an assortment level: a = basic, b = extra, c = extended\n\nCompetitionDistance - distance in meters to the nearest competitor store\n\nCompetitionOpenSince[Month/Year] - gives the approximate year and month of the time the nearest competitor was opened\n\nPromo - indicates whether a store is running a promo on that day\n\nPromo2 - Promo2 is a continuing and consecutive promotion for some stores: 0 = store is not participating, 1 = store is participating\n\nPromo2Since[Year/Week] - describes the year and calendar week when the store started participating in Promo2\n\nPromoInterval - describes the consecutive intervals Promo2 is started, naming the months the promotion is started anew. E.g. \"Feb,May,Aug,Nov\" means each round starts in February, May, August, November of any given year for that store",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "Description",
      "content": "Rossmann operates over 3,000 drug stores in 7 European countries. Currently, Rossmann store managers are tasked with predicting their daily sales for up to six weeks in advance. Store sales are influenced by many factors, including promotions, competition, school and state holidays, seasonality, and locality. With thousands of individual managers predicting sales based on their unique circumstances, the accuracy of results can be quite varied.\n\nIn their first Kaggle competition, Rossmann is challenging you to predict 6 weeks of daily sales for 1,115 stores located across Germany. Reliable sales forecasts enable store managers to create effective staff schedules that increase productivity and motivation. By helping Rossmann create a robust prediction model, you will help store managers stay focused on what’s most important to them: their customers and their teams! ",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "Evaluation",
      "content": "Submissions are evaluated on the Root Mean Square Percentage Error (RMSPE). The RMSPE is calculated as\n\n![][1]\n\nwhere y_i denotes the sales of a single store on a single day and ŷ_i denotes the corresponding prediction. Any day and store with 0 sales is mapped to 1.\nPlease refer to IVLE forum for more discussions on evaluation in case of 0 sales. \n\n\n## Submission File\n\nThe file should contain a header and have the following format:\n\nId,Sales\n\n1,0\n\n2,0\n\n3,0\n\netc.\n\n\n  [1]: http://www.amydotnet.com/wp-content/uploads/2015/12/equation.png",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    }
  ]
}