An end-to-end machine learning application for predicting depression risk based on user lifestyle and stress-related inputs, deployed with Streamlit and Hugging Face.

description for github repoMachine learning project predicting depression risk from demographic, academic/work, and lifestyle data using Random Forest, XGBoost, and CatBoost (93-94% accuracy).

Demonstrate a comprehensive understanding of current advanced methods and techniques in data and text analytics. Design and implement data mining based applications to solve real-world problems. Critically analyse and evaluate the performance of different data mining techniques for text analysis and analyse and interpret the data mining results.

🧠 ML web app predicting student depression risks. Showcases a complete pipeline: baseline modeling, advanced data preprocessing, and optimized Logistic Regression.

A Machine Learning and Streamlit-based application for analyzing teen mental health patterns and predicting depression risk using social media usage, sleep habits, stress levels, anxiety, academic performance, and lifestyle factors.

Projet de data science appliqué à la prédiction de la dépression avec optimisation des modèles et des variables