Hnin Oo Wai

Machine Learning-Driven Prediction and Analysis of Mental Health Risks Among University Students

• Published, IEEE Conference/ 2025 22nd International Joint Conference on Computer Science and Software Engineering(JCSSE)
• Applied Random Forest, XGBoost and Deep Learning models to predict student mental health risk
• Performed clustering and correlation analysis on behavioural survey data
• Achieved 90.6% prediction accuracy in identifying mental health risks among university students and revealed key behavioural risk factors.
• Tools : Rapid Miner, Excel, Machine Learning

Mining Student Behaviour Patterns for Mental Health Insights using Association Rule Learning

• Published, IEEE Conference/ 2025 9th International Conference on Information Technology(INCIT)
• Used FP-Growth and Association Rule Mining to identify behavioural patterns linked to mental health
• Analysed lifestyle, financial and psychosocial factors
• Discovered interpretable behavioural patterns linking sleep, coping strategies, screen time, and financial support to student mental health outcomes.
• Tools: RapidMiner, Excel

Integrating Machine Learning into Consumer Behaviour Analysis for Insect-Based Protein Supplements

• Accepted(In Press), 2026 18th International Conference on Knowledge and Smart Technology(KST)
• Conducted classification, clustering and association rule mining on consumer survey data
• Achieved 76.1% accuracy in predicting consumer acceptance of insect-based protein products.
• Tools: RapidMiner, Excel, Machine Learning