{
  "fetched_at": "2026-10-20T08:46:20Z",
  "source_url": "https://www.kaggle.com/competitions/beginners-prediction-task/data",
  "pages": [
    {
      "name": "data-description",
      "content": "The Student GPA Prediction Competition dataset contains data on over 400 students. The data set includes information on the students' demographics, academic performance, and other factors. The data set is divided into two parts: a training set and a test set. The training set contains data students and is used to train machine learning models. The test set contains data students and is used to evaluate the performance of the machine learning models.\n\nThe data set includes the following features:\n\nGender: The student's gender.\nEthnicity: The student's ethnicity.\nReligion: The student's religion.\nState of origin: The student's state of origin.\nAge: The student's age.\nHobby: The student's hobby.\nSchool type: The type of school the student attends.\nParental education level: The highest level of education attained by the student's parents.\nExtracurricular activity: The student's extracurricular activities.\nLearning disability: Whether the student has a learning disability.\nSchool location: The location of the student's school.\nTutoring/mentoring program: Whether the student participates in a tutoring or mentoring program.\nParental involvement level: The level of parental involvement in the student's education.\nBullying experience: Whether the student has been bullied.\nStudy time: The number of hours per week the student studies.\nAttendance percentage: The student's attendance percentage.\nSelf-motivation level: The student's self-motivation level.\nStudy environment rating: The student's study environment rating.\nStress level: The student's stress level.\nParental support rating: The student's parental support rating.\nNote-taking habits: The student's note-taking habits.\nNumber of extracurricular activities participated: The number of extracurricular activities the student participates in.\nNumber of leadership roles held: The number of leadership roles the student holds.\nTeacher quality rating: The student's teacher quality rating.\nNumber of school resources available: The number of school resources available to the student.\nPeer interaction level: The student's peer interaction level.\nExam maths: The student's exam maths score.\nExam english: The student's exam english score.\nExam social science: The student's exam social science score.\nGPA: The student's GPA.\nThe data set is available for download from the Kaggle website.\n\n### Data Description\n\nThe Data Description file provides more detailed information about the features in the dataset. The file includes the following information for each featurSample Submission\nThe Sample Submission file provides an example of the format that the submissions should be in.\n\n### Conclusion\nThe Student GPA Prediction Competition dataset is a valuable resource for learning about the factors that contribute to student success. The data could be used to develop new interventions and programs to help students succeed in school. I hope you will participate in the competition!\n\n\n\n## Files\n\n*   **train.csv** - the training set\n*   **test.csv** - the test set\n*   **sample_submission.csv** - a sample submission file in the correct format\n*   **metaData.csv** - supplemental information about the data\n\n## Columns\n\n*   `example_id` - random 8 character\n*   `gpa` - float\n*   etc.",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "Description",
      "content": "Predict Student GPA\n\nIn this competition, you will use data on student demographics, academic performance, and other factors to predict student GPA. The data set includes over 100 features, such as gender, ethnicity, religion, state of origin, age, hobby, school type, parental education level, extracurricular activity, learning disability, school location, tutoring/mentoring program, parental involvement level, bullying experience, study time, attendance percentage, self-motivation level, study environment rating, stress level, parental support rating, note-taking habits, number of extracurricular activities participated, number of leadership roles held, teacher quality rating, number of school resources available, peer interaction level, exam maths, exam english, exam social science, and GPA.\n\nThe competition will be evaluated using the Root Mean Square Error (RMSE) metric. The participant with the lowest RMSE will be the winner of the competition.\n\nThe competition is open to all participants. There is no entry fee.\n\nTo participate in the competition, you will need to create a Kaggle account and submit your predictions for the student's GPA. You can submit your predictions as often as you like. The final predictions will be evaluated on the test set.\n\nThe competition is a valuable opportunity to learn about the factors that contribute to student success. The data could be used to develop new interventions and programs to help students succeed in school.\n\nI hope you will participate in the competition!",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "Evaluation",
      "content": "The competition will be evaluated using the Root Mean Square Error (RMSE) metric. The RMSE metric is a measure of the average error between the predicted values and the actual values. The lower the RMSE, the better the predictions.\n\nThe RMSE is calculated as follows:\n\n\n`RMSE = sqrt(mean( (actual - predicted)^2 ))`\n\n**where:**\n\n- actual is the actual value\n- predicted is the predicted value\n- mean is the average\n\nThe RMSE metric is a good for regression competitions because it is a measure of the overall error in the predictions. The RMSE metric is not affected by outliers, which are extreme values that can skew the results of other evaluation metrics, such as the Mean Absolute Error (MAE).\n\nThe participant with the lowest RMSE will be the winner of the competition.",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "rules",
      "content": "here are the rules for the Student GPA Prediction Competition:\n\n**Eligibility**: The competition is open to all participants. There is no entry fee.\n\n**Data**: The data set will be released on 28 May, 2023. The data set includes over 100 features, such as gender, ethnicity, religion, state of origin, age, hobby, school type, parental education level, extracurricular activity, learning disability, school location, tutoring/mentoring program, parental involvement level, bullying experience, study time, attendance percentage, self-motivation level, study environment rating, stress level, parental support rating, note-taking habits, number of extracurricular activities participated, number of leadership roles held, teacher quality rating, number of school resources available, peer interaction level, exam maths, exam english, exam social science, and GPA.\n\n**Submissions**: Submissions will be accepted from May 28, 2023 to March 31, 2024. Participants can submit their predictions as often as they like. The final predictions will be evaluated on the test set.\n\n**Evaluation**: The competition will be evaluated using the Root Mean Square Error (RMSE) metric. The participant with the lowest RMSE will be the winner of the competition.\n\n**Leaderboard**: The leaderboard will be updated daily with the latest scores from the participants. The leaderboard will be sorted by the RMSE metric. The participant with the lowest RMSE will be at the top of the leaderboard.\n\n### Rules:\n The following rules apply to the competition:\n\n- Participants must agree to the competition rules before participating.\n\n- Participants must use the provided data set to make their predictions.\n\n- Participants must not use any external data or resources to make their predictions.\n\n- Participants must not submit multiple submissions for the same prediction.\n\n- Participants must not engage in any behavior that could be considered cheating or unfair.\n\nAny participant who violates the competition rules will be disqualified.\n\n",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    }
  ]
}