Featured Projects
A collection of technical projects, research initiatives, and practical applications showcasing my skills in data science, machine learning, finance, and software development.
My Project Approach
Problem Definition
Identify real-world challenges and define clear objectives
Technical Solution
Design and implement data-driven solutions using appropriate tools
Impact & Learning
Evaluate results, document learnings, and iterate for improvement
Featured Projects
Alopecia Areata Risk Model & Shiny App
Gene expression classification using GSE68801 dataset. Built LASSO/SVM/Random Forest models with deployed Shiny risk calculator.
Problem
Need for early detection and risk assessment of Alopecia Areata using gene expression data
Approach
Applied multiple ML algorithms (LASSO, SVM, Random Forest) to gene expression data and deployed interactive Shiny app for risk calculation
Impact
ROC analysis showed 85% accuracy, with high sensitivity and specificity for early detection
Diabetic Nephropathy SVM Classification
SVM classification exploring SRGAP2 expression using GSE96804 dataset. Comprehensive EDA with PCA, heatmaps, and limma analysis.
Problem
Understanding the role of SRGAP2 in diabetic nephropathy progression
Approach
Comprehensive exploratory data analysis followed by SVM classification with feature selection and model evaluation
Impact
Identified key biomarkers and achieved 82% classification accuracy with robust cross-validation
Stock Volatility Prediction
Engineered features and trained Linear Regression, Random Forest, XGBoost models. Added GARCH(1,1) for time-varying volatility analysis.
Problem
Predicting stock price volatility for better risk management and trading decisions
Approach
Feature engineering from market data, ensemble ML models, and GARCH time series analysis for volatility clustering
Impact
Improved volatility prediction accuracy by 23% compared to baseline models, enabling better risk assessment
Capital Structure Analysis - CSL Limited
CSL Limited (ASX: CSL) 2019-2024 peer comparison with leverage drivers analysis and strategic recommendations.
Problem
Understanding CSL's capital structure and providing strategic recommendations for optimal financing
Approach
Comprehensive analysis of leverage ratios, peer comparison, and identification of key capital structure drivers
Impact
Provided actionable recommendations that could optimize CSL's cost of capital by 15-20 basis points
Multi-Model AI Agent
Local LLM workflow with task orchestration, agent specialization, and ephemeral concurrency using Llama 3.3 70B and Phi-4 14B.
Problem
Need for efficient local AI agent systems that can handle multiple specialized tasks concurrently
Approach
Designed modular agent architecture with task orchestration, model specialization, and ephemeral concurrency management
Impact
Reduced inference time by 40% while maintaining task quality through intelligent model routing
Additional Projects
EDU Chat - Student Collaboration App
Student collaboration application with full project management artifacts including business case, WBS, risk assessment, and quality planning.
Drone Content & UAV Operations
Content strategy and compliance research for Australian UAV regulations. Social media operations and regulatory compliance management.