{
  "fetched_at": "2026-10-20T01:49:33Z",
  "source_url": "https://www.kaggle.com/competitions/2020wintermidterm/data",
  "pages": [
    {
      "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!",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "data-description",
      "content": "What's in the Zip? \n\n- week_7_data_dictonary.docx - a data dictionary - describing the fields of the datasets\n- train.csv - the training data set\n- test.csv - the test data set\n- predict.csv - the test data you will predict your results with\n- zips.csv - data set of zip codes\n- sampleSubmission.csv - a sample submission file in the correct format",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "Description",
      "content": "In this project you will draw on your SAS skills to predict assessed values for the city of Boston. I've provided 4 files train, test, predict and zip which you’ll have to put together. You’ll then explore and prepare the data for modeling. Next, you’ll build and document regression models to predict home values (AV_TOTAL), finally you’ll have to predict home values on an out-of-sample predict dataset. I’ve set up this Kaggle competition where you’ll publish your out-of-sample dataset and compare your model against your peers.\n\n## Problem\n\nYou now work for a major financial institution as a data scientist, in the mortgage valuation department. You have been asked to build a new regression model that will predict the market value of properties in order to determine how much money to loan a potential buyer. The target that you are attempting to predict is the assessed value column (AV_TOTAL)\n\nYou are provided three CSV files:\n\n• Training.csv – this is the data set you’ll train your regression models with\n\n• Validation.csv – this is the data set you’ll use to validate your regression models with\n\n• Prediction.csv – this is the \"test\" data set you’ll predict “assessed value”\n\n## You must beat the benchmark submission!\n\nThe benchmark RMSE is 115350.9 that means you must have a score LESS than this! ",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "Evaluation",
      "content": "You'll be evaluated on your model's  root-mean-square error (RMSE). RMSE is a frequently used measure to assess the accuracy of regression models. \n\nRoot Mean Square Error (RMSE) is the standard deviation of the residuals (prediction errors). Residuals are a measure of how far from the regression line data points are; RMSE is a measure of how spread out these residuals are. In other words, it tells you how concentrated the data is around the line of best fit.\n\nSQRT(MEAN(y - y')^2)) \n\nSquare **R**oot of the **M**ean or **S**quared **E**rror (actual minus predicted) \n",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    }
  ]
}