{
  "fetched_at": "2026-10-20T06:31:10Z",
  "source_url": "https://www.kaggle.com/competitions/faim-sgp-25-j-sarah-gets-a-diamond/data",
  "pages": [
    {
      "name": "data-description",
      "content": "The file “Sarah Gets a Diamond data.xls” contains data about various attributes for over 9000 diamonds. For the first 6000 you also have the price.\n\nThe goal of this competition is to use the tools you've learned in previous courses to predict the prices of the remaining diamonds (i.e., those with IDs 6001 and above).\n\n## Files\n\n*   **Sarah Gets a Diamond data.xls** - the dataset from the case \n\n## Columns\n\n*   names are self-explanatory and discussed in the case",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "Description",
      "content": "Case: “Sarah Gets a Diamond”, UVA-QA-0702 + data\n\nThe file “Sarah Gets a Diamond data.xls” contains data about various attributes for over 9000 diamonds. For the first 6000 you also have the price. \n\nThe goal of this competition is to use the concepts and tools you've learned in Sessions 2-4 to predict the prices of the remaining diamonds (i.e., those with IDs 6001 and above). \n\nWhen done, create a spreadsheet containing two columns: ID and Price. For IDs, put 6001, 6002, etc., and for the prices, put the numerical values of your predictions (without dollar signs, or any other strings), e.g., 12345.6, 23456.7, etc.\n\nSave the resultant file in the CSV format and submit it. Make sure the column names follow the uppercase and lowercase format and are exactly ID and Price:\n![](https://www.googleapis.com/download/storage/v1/b/kaggle-user-content/o/inbox%2F1489777%2F9cc19c90fa3db1214edc371261ef142c%2FSarah%20Gets%20a%20Diamond%20solution%20-%20sample.JPG?generation=1734625749156314&alt=media)\n\nYour submission will be immediately scored on a fraction of the diamonds according to the Mean Absolute Percentage Error (MAPE) metric that we will discuss in class. The lower, the better. \n\n## Acknowledgements\n\nhttp://store.darden.virginia.edu/sarah-gets-a-diamond ",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "Evaluation",
      "content": "The goal of this competition is to use the tools you've learned in Sessions 2-4 to predict the prices of the remaining diamonds (i.e., those with IDs 6001 and above).\n\nWhen done, create a spreadsheet containing two columns: ID and Price. For IDs, put 6001, 6002, etc., and for the prices, put the numerical values of your predictions (without dollar signs, or any other strings), e.g., 12345.6, 23456.7, etc.\n\nSave the resultant file in the CSV format and submit it. Make sure the column names follow the uppercase and lowercase format and are exactly ID and Price. See the example in the Description section. \n\nYour submission will be immediately scored on a fraction of the diamonds according to the Mean Absolute Percentage Error (MAPE) metric that we will discuss in class. The lower, the better.\n\n",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "rules",
      "content": "Competition rules: \n\n - Work in your course groups\n - Use the ordinary least squares (OLS) regression methods as studied in Sessions 2-4, including the advanced ones with feature engineering, regularizations, and other \"twists.\" Note, there exist other methods which we have not studied yet. You are free to explore them, but if your group decides to try non-regression methods (e.g., a random forest, which we will discuss in Session 5-6), please create two different Kaggle teams for your submissions to not mix up regression and non-regression results (e.g., G1_regression, and G1_random_forest). The regression results will be graded, but it could be insightful to see how much better other methods can do.\n - Have fun!",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    }
  ]
}