Machine Learning-Based Intervention Recommendation System for Student Stress Management
- Version
- Download 43
- File Size 272.64 KB
- File Count 1
- Create Date 2 May 2025
- Last Updated 2 May 2025
Machine Learning-Based Intervention Recommendation System for Student Stress Management
Authors:
Dr. Sonali Nemade1, Mrs. Reshma Masurekar2, Ms. Ashwini Patil3 , Mr. Satyawan Kunjir4
1Dr. Sonali Nemade, Computer Science Department & Dr. D. Y. Patil Arts, Commerce, Science College, Pimpri
2Mrs. Reshma Masurekar, Computer Science Department & Dr. D. Y. Patil Arts, Commerce, Science College, Pimpri
3Ms. Ashwini Patil Computer Science Department & Dr. D. Y. Patil Arts, Commerce, Science College, Pimpri
4Mr. Satywan Kunjir Computer Science Department & Dr. D. Y. Patil Arts, Commerce, Science College, Pimpri
Abstract - The growing number of students facing mental health problems emphasizes how urgently proactive, individualized stress management strategies are needed. This study suggests a Machine Learning-Based Intervention Recommendation System (MLIRS) that predicts stress levels and suggests customized therapies by analyzing behavioral, academic, and physiological data from students. Academic records, wearable technology, and questionnaires are all integrated into the system to collect data. We use three supervised learning models to categorize stress levels: Random Forest, Support Vector Machine (SVM), and Gradient Boosting. A recommendation engine that combines collaborative and content-based filtering methods makes recommendations for relevant treatments. A real-world student dataset evaluation reveals a 92% prediction accuracy and excellent user satisfaction with the suggested interventions.
Key Words: Student Stress, Machine Learning, Stress Detection, Intervention Recommendation, Mental Health, Hybrid Recommender System, Academic Performance, Predictive Analytics
Download