🎓 Information Technology & Management graduate (degree completed, awaiting graduation) from the Faculty of Science, University of Colombo — with a GPA of 3.47/4.00
🔍 Passionate about transforming raw data into actionable business intelligence through machine learning, analytics, and visualization
🤖 Currently exploring Deep Learning, advanced SQL optimization, and MLOps & Model Deployment
💡 Open to collaborations on data science projects, HR analytics, and ML-powered tools
"Data is the new oil. It's valuable, but if unrefined it cannot really be used." — Clive Humby
| Category | Tools |
|---|---|
| Languages | Python · SQL / T-SQL · Jupyter Notebook |
| ML & Data | Scikit-learn · Pandas · NumPy · TF-IDF · NLP · PyTorch · TensorFlow |
| Visualization | Power BI · Matplotlib · Seaborn · Streamlit |
| Databases | Microsoft SQL Server · MySQL · MongoDB |
| Dev Tools | Git · GitHub · VS Code · Google Colab |
| 🤖 Machine Learning | 📊 Data Analytics | 👥 HR Analytics |
| NLP · Scikit-learn · Predictive Models | SQL · Power BI · KPI Dashboards | Workforce Planning · Forecasting |
| 🏪 Retail Analytics | 🧠 NLP & Text Mining | 📈 Business Intelligence |
| Sales Analysis · BI Reporting | TF-IDF · Cosine Similarity · CV Matching | Decision Support · Trend Analysis |
Predictive workforce planning using historical HR recruitment data — includes data cleaning, exploratory analysis, forecasting models, and visual dashboards to anticipate future hiring needs by department.
A content-based job recommendation system built that matches candidates to relevant job postings using NLP and cosine similarity.
AI-powered predictive blockchain system for Sri Lankan pharmaceutical supply chain management.
A deep learning project applying NLP techniques to recruitment data — including resume classification, job-description matching, and keyword extraction using TF-IDF and feedforward neural networks.
Time series forecasting and market trend analysis of Sri Lankan recruitment industry (2022-2024) using Python, Prophet, and Power BI. Includes data cleaning, forecasting models, scenario analysis, and interactive PowerBI dashboards.
A comparative study of XGBoost and Random Forest ensemble models for predicting employee attrition using the IBM HR Analytics dataset. Includes EDA, preprocessing, hyperparameter tuning, feature importance analysis with SHAP, and a final performance comparison.