Data Scientist | Machine Learning - Deep Learning - Artificial Intelligence - Analytics - Decision Intelligence
Welcome to my GitHub.
I’m a Data Scientist focused on building reproducible, decision-oriented data products—from data preparation and statistical analysis to ML/DL modeling, NLP/LLM applications, and analytics engineering that supports trustworthy dashboards and business decisions.
My foundation blends quantitative rigor (Mathematics & Science Education), human-centered analysis (Sociology), and systems + business thinking (MIS + MBA-level coursework), supported by project management discipline (PMI-aligned training) and real-world responsibility through leadership and volunteer work.
- End-to-End Data Science Pipelines (EDA → Feature Engineering → Modeling → Evaluation → Deployment)
- Statistical Analysis, Experiment Design & Model Interpretability
- Machine Learning (Supervised & Unsupervised Learning)
- Deep Learning (Neural Networks; practical model building & evaluation)
- Natural Language Processing (NLP) & LLM Applications (Embeddings, Semantic Search, RAG)
- Analytics Engineering (ELT/ETL, warehouse-friendly modeling, dbt-style transformations)
- BI & Decision Support (KPI design, executive dashboards, stakeholder storytelling)
Note: Tooling listed reflects the environments I’ve used across academic programs and hands-on analytics/ML workflows.
- Regression, Classification, and Clustering
- Feature Engineering, Leakage-Safe Validation, and Robust Evaluation
- Cross-Validation, Hyperparameter Optimization, and Model Selection
- Interpretable ML (feature importance, error analysis, calibration mindset)
- Neural Networks (MLP/CNN/RNN fundamentals; practical training & evaluation)
- NLP workflows (tokenization, embeddings, text classification, similarity search)
- LLM applications: Prompting, tool-usage patterns, RAG, semantic search
- Reproducibility mindset: experiment tracking habits, clean notebooks → scripts
- Analytics engineering (warehouse modeling, clean marts, documented metrics)
- SQL for scalable reporting and trustworthy KPI layers
- Data quality habits (sanity checks, assumptions, reproducible transformations)
- KPI frameworks: clarity, consistency, metric definitions, drill-down design
- Executive-ready storytelling (CEO/CFO views, segmentation, cohorts, trends)
- Dashboard usability: filters/controls, naming, semantics, and interpretation
- B.A. Sociology — Human behavior, society, and qualitative/quantitative perspectives
- B.Sc. Mathematics & Science Education — Strong quantitative reasoning, structured problem solving, pedagogy
- M.Sc. Management Information Systems (MIS) — Systems thinking, business analytics, data-driven strategy
- MBA-level Coursework (within MIS curriculum) — Business Analytics, CRM, Sustainable Management, Big Data Management, Value Chain, Project Management, Research Methods, Low-Code App Development
- PMI-aligned Project Management training (planning, scope, risk, communication cadence)
- Agile mindset (iterative delivery, clear milestones, stakeholder alignment)
- High-responsibility volunteering in Search & Rescue (discipline, teamwork, decision-making under pressure)
I build projects with real-world framing, clean documentation, and reproducible pipelines:
- End-to-End ML Projects (from raw data → validated models → delivery-ready outputs)
- Market Basket Analysis & Recommendation Systems
- Customer Segmentation & Behavioral Analytics
- NLP & LLM-Based AI Applications (Embeddings, Semantic Search, RAG)
- KPI-Driven Dashboards & Decision Support
- Structured thinking + practical execution
- Transparent assumptions, clean pipelines, reliable evaluation
- Strong communication (teaching background; executive-friendly outputs)
- Collaborative and disciplined delivery habits