Computer Science (AI) · University of Malaya
Tanvir Hossain
Always one question deep and one prototype away.
I'd rather build things people actually use than things that only impress other engineers. Most of what I make leans on machine learning, and I care most about the step where a model leaves the notebook and reaches people.
Work
Student Performance Predictor
Feb 2025Analysed 6,600 student records to identify key factors behind exam performance. Developed and compared Linear Regression, Decision Tree, and Neural Network models.
Medical Cost Prediction
Jul 2026Predicts individual medical insurance charges from personal attributes, built to understand model behaviour rather than chase scores. Compared seven regression models and engineered interaction features around the dataset's three cost bands: linear models plateau at R² 0.87 while Random Forest cuts MAE to around $1,960.
BadDebtGuard AI
Dec 2025Credit risk assessment system combining structured financial data with unstructured borrower text. Uses XGBoost for numerical features and an LLM+RAG pipeline to extract behavioural signals from loan essays and bank statements.
About
Based
Kuala Lumpur, Malaysia
From
Cumilla, Bangladesh
Study
Sophomore · CS (AI) · UM
Speak
বাংলা · English · Hindi/Urdu
Contact
My inbox is open.
Kuala Lumpur, GMT+8.