Overview
EduPulse is a lightweight machine learning model trained on a dataset of 2,000 student records, capturing daily habits across study, sleep, extracurriculars, socializing, and physical activity. The model predicts GPA and estimates stress levels derived from study and sleep hours. It is designed to support research and applications in education, psychology, and health.

Intended Uses
Academic performance prediction

Lifestyle and well-being assessment

Educational research and student support tools

Stress level estimation based on daily habits

Model Architecture
Random Forest

Framework: [e.g., scikit-learn, PyTorch, TensorFlow]

Input Features:

Study hours

Sleep hours

Extracurricular activity hours

Socializing hours

Physical activity hours

Output:

Predicted GPA

Estimated stress level (derived feature)

Training Data
Dataset Size: 2,000 student records

Source: Synthetic or anonymized real-world data

Features: Lifestyle habits, GPA, derived stress level

Preprocessing:

Normalization of hours

Feature engineering for stress level

Train-test split: 80/20