Student Exam Score Predictor

This Data Management Plan (DMP) outlines the data collection, organization, sharing, and reuse strategy for the project titled "Student Exam Score Predictor", developed as part of the FAIR Data Science exercise at TU Wien. The project uses a structured synthetic dataset that contains five columns: Student_ID: unique identifier for each student Study_Hours: number of hours the student studied Attendance_Percentage: student's class attendance Previous_Exam_Score: score obtained in a prior exam Final_Exam_Score: the target variable predicted by the model A supervised machine learning model (Linear Regression) was trained to predict final exam scores based on study hours and other student-related performance metrics. The dataset was manually curated and does not include personal or sensitive data. This DMP includes all relevant metadata standards (FAIR4ML, CodeMeta), describes the input/output structure, and explains how data and model artifacts are made findable, accessible, interoperable, and reusable (FAIR). All components of the project — data, model, documentation, and metadata — are publicly available and licensed under permissive terms to encourage reuse.