{
  "fetched_at": "2026-10-20T04:09:54Z",
  "source_url": "https://www.kaggle.com/competitions/asrm-455/data",
  "pages": [
    {
      "name": "data-description",
      "content": "Data Dictionary Summary\n\n**days**: Number of days between hospital admission and discharge.\nType: Integer (1-14)\n\n**gender**: Patient’s gender.\nValues: Female, Male\n\n**age**: Age of the patient grouped in ten-year intervals.\nValues: [0, 10), [10, 20), …, [90, 100)\n\n**race**: Patient’s race/ethnicity.\nValues: AfricanAmerican, Asian, Caucasian, Hispanic, Other\n\n**weight**: Patient’s weight, categorized in twenty-five-pound intervals.\nValues: [0, 25), [25, 50), …, [175, 200)\n\n**admit_type_id**: Type of hospital admission.\nValues:\n1 = Emergency\n2 = Urgent\n3 = Elective\n4 = Not Available\n\n**metformin**: Indicates whether metformin was prescribed or if there was a change in dosage upon admission.\nValues:\nUp = dosage increased\nDown = dosage decreased\nSteady = no change in dosage\nNo = not prescribed\n\n**insulin**: Indicates whether insulin was prescribed or if there was a change in dosage upon admission.\nValues:\nUp = dosage increased\nDown = dosage decreased\nSteady = no change in dosage\nNo = not prescribed\n\n**readmitted**: Indicates whether the patient had been readmitted within 12 months prior to the encounter.\nValues:\nNo  = no record of readmission\n**<**=readmitted in less than 30 days\n**>**= readmitted in more than 30 days  \n\n\n**num_procs**:Number of procedures performed in the 12 months prior to the encounter.\nType: Integer (0-6)\n\n**num_meds**:Number of distinct medications administered in the 12 months prior to the encounter.\nType: Integer (1-67)\n\n**num_ip**: Number of inpatient visits in the 12 months prior to the encounter.\nType: Integer (0-21)\n\n**num_diags**:Number of diagnoses entered into the system in the 12 months prior to the encounter.\nType: Integer (1-16)",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "Description",
      "content": "This is a open project on data analytics. You are expected to perform data analysis, preprocessing, model selection, feature selection, … based on the prediction task.\n\nYou may consult resources like textbooks and Internet materials. You may use any analytics software to complete the analysis as instructed. However, you may not discuss the specific business problem, data, or tasks with others.",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "Evaluation",
      "content": "1. Grading and Submission Details:\nThis document and the report template indicate the points assigned to each of the components, totaling 100 points. Grading criteria include:\n• Quality of thought process\n• Code\n• Conclusions and clarity in the report\nWhen instructed, include specific output (tables or graphs) in your response. These are required at minimum, but displaying additional relevant output is encouraged.\n\n2. Submission Requirements in Canvas\nAt a minimum, submit:\n• A completed report template (Word, .docx) containing your task responses.\n• An .Rmd file that supports your analysis. This file should run from start to finish and clearly indicate.Your thought process and conclusions for each task must be fully contained within your Word report. The. Rmd file should be clear, may contain comments, and should directly support the analysis provided in your report.\n\n3. For Kaggle Submission:\nYour submission file should be a CSV with the following structure:\n\nID: This should be the numbers 1 to 4, each corresponding to a specific metric.\nValue: This should contain the values for the following metrics, in this order:\n- AUC_Train_classification\n- AUC_Test_classification\n- Pearson goodness-of-fit statistic on training data\n- Pearson goodness-of-fit statistic on testing data\nMake sure your file format and column names exactly match the competition specifications to avoid errors during scoring.\n",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "rules",
      "content": "- The University of Illinois at Urbana-Champaign Student Code should also be considered as a part of this project. Students should pay particular attention to Article 1, Part 4: Academic Integrity. Read the Code at the following URL: http://studentcode.illinois.edu/.\n- Academic dishonesty may result in a failing grade. Every student is expected to review and abide by the Academic Integrity Policy: http://studentcode.illinois.edu/. Ignorance is not an excuse for any academic dishonesty. It is your responsibility to read this policy to avoid any misunderstanding. Do not hesitate to ask the instructor if you are ever in doubt about what constitutes plagiarism, cheating, or any other breach of academic integrity.",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "abstract",
      "content": "This is the individual project/in-class Kaggle competition of ASRM 455  Predictive\nAnalytics Fall 2024 ",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    }
  ]
}