Higher Education Student Outcomes Prediction

Columns

• Marital status: The student's marital status, coded numerically (e.g., 1 – single, 2 – married).
• Application mode: The method of application used by the student, coded numerically for various application phases and special contingents.
• Application order: The student's application preference, ranging from 0 (first choice) to 9 (last choice).
• Course: The specific undergraduate course the student is enrolled in, represented by numerical codes for various fields such as Agronomy, Design, Education, Nursing, Journalism, Management, Social Services, and Technology.
• Daytime/evening attendance: Indicates if the student attends classes during the day (1) or in the evening (0).
• Previous qualification: The qualification obtained by the student prior to higher education enrolment, coded numerically for different levels (e.g., secondary education, bachelor's degree).
• Previous qualification (grade): The grade achieved in the previous qualification, ranging from 0 to 200.
• Nacionality: The student's nationality, represented by numerical codes (e.g., 1 - Portuguese, 41 - Brazilian).
• Mother's qualification: The educational qualification of the student's mother, coded numerically.
• Father's qualification: The educational qualification of the student's father, coded numerically.
• Mother's occupation: The occupation of the student's mother, coded numerically for various professional categories.
• Father's occupation: The occupation of the student's father, coded numerically for various professional categories.
• Admission grade: The student's admission grade, ranging from 0 to 200.
• Displaced: Indicates if the student is a displaced person (1 – yes, 0 – no).
• Educational special needs: Indicates if the student has any special educational needs (1 – yes, 0 – no).
• Debtor: Indicates if the student is a debtor (1 – yes, 0 – no).
• Tuition fees up to date: Indicates if the student's tuition fees are up to date (1 – yes, 0 – no).
• Gender: The student's gender (1 – male, 0 – female).
• Scholarship holder: Indicates if the student is a scholarship holder (1 – yes, 0 – no).
• Age at enrollment: The student's age at the time of enrolment.
• International: Indicates if the student is an international student (1 – yes, 0 – no).
• Curricular units 1st sem (credited): The number of curricular units credited in the first semester.
• Curricular units 1st sem (enrolled): The number of curricular units the student enrolled in during the first semester.
• Curricular units 1st sem (evaluations): The number of evaluations for curricular units in the first semester.
• Curricular units 1st sem (approved): The number of curricular units approved in the first semester.
• Curricular units 1st sem (grade): The average grade in the first semester, between 0 and 20.
• Curricular units 1st sem (without evaluations): The number of curricular units without evaluations in the first semester.
• Curricular units 2nd sem (credited): The number of curricular units credited in the second semester.
• Curricular units 2nd sem (enrolled): The number of curricular units the student enrolled in during the second semester.
• Curricular units 2nd sem (evaluations): The number of evaluations for curricular units in the second semester.
• Curricular units 2nd sem (approved): The number of curricular units approved in the second semester.
• Curricular units 2nd sem (grade): The average grade in the second semester, between 0 and 20.
• Curricular units 2nd sem (without evaluations): The number of curricular units without evaluations in the second semester.
• Unemployment rate: The unemployment rate (%).
• Inflation rate: The inflation rate (%).
• GDP: Gross Domestic Product (GDP).
• Target: The classification target, indicating if the student is 'dropout', 'enrolled', or 'graduate' at the end of the course.

Distribution

Usage

• Developing machine learning models for early prediction of student dropout and academic success in higher education.
• Identifying key factors influencing student performance.
• Informing intervention strategies and support programmes for at-risk students.
• Academic research into educational data mining and predictive analytics.

Coverage

License

Who Can Use It

• Data Scientists and Machine Learning Engineers working on predictive modelling in education.
• Researchers and Academics in the fields of higher education, educational psychology, and data analytics.
• University Administrators and Policymakers interested in student retention and success programmes.
• Students undertaking projects related to educational outcomes and data-driven interventions.

Dataset Name Suggestions

• Higher Education Student Outcomes Prediction
• Portuguese University Student Performance Indicators
• Academic Dropout Prediction (Portugal)
• Polytechnic Institute Student Success Data
• Student Academic Risk Analysis Dataset

Attributes