Applied work across analytics engineering, machine learning, forecasting, BI, geospatial analytics, and agentic AI-assisted workflows. Each entry emphasizes the problem, data approach, modeling or system design, and decision-support value.
Public repositories are linked directly. Private materials are summarized only at a capability level.
Repository material supporting the Azure AI Document Intelligence and Power Platform case study, focused on scanned-report extraction, validation, and reporting workflows.
Fraud-detection modeling work around tabular transaction data, feature preparation, and classification-oriented experimentation.
Applied regression project for house-price prediction, useful as a compact example of exploratory analysis, modeling, and error evaluation.
Classification exercise focused on medical-risk style tabular data, model comparison, and practical prediction workflow design.
Small data-ingestion project that complements the portfolio themes around repeatable data movement, automation, and pipeline setup.
Private Power BI budget-dashboard material. The portfolio references the capability while keeping internal files and repository details unpublished.
A local multi-agent stock research platform where LLM orchestration is separated from deterministic diagnostics, forecasting, and backtesting.
A CLI-first multi-agent research platform for literature discovery, proposal generation, peer review, and dissertation-aware planning.
Private Power BI working project focused on budget and revenue visibility, data modeling, and executive-ready financial reporting.
Private multi-agent research platform for literature discovery, proposal generation, peer review, and dissertation-aware planning.
Private multi-agent analytics platform for stock research, deterministic diagnostics, forecasting comparisons, backtesting, and opportunity scoring.
Built a low-cost cloud routing workflow combining ArcGIS, Azure Functions, Blob Storage, Power Automate, and Power BI to automate daily geo-routing operations.
Designed an OCR-driven reporting workflow using Azure AI Document Intelligence, Power BI, Power Apps, and Power Automate to replace manual document processing.
Compared Azure AutoML with a custom Jupyter-based modeling workflow for shipping-cost prediction, focusing on tradeoffs in speed, control, and model quality.
Explored DNS and web-log data as an analytics source for observability, anomaly detection, and operational planning.
Modeled forex-related tweets as a graph to study market actors, event types, hashtags, concepts, and relationship patterns.
Designed a Power BI row-level security model to control enterprise data access by role while preserving reporting flexibility for leaders and managers.
Integrated ArcGIS into Power BI dashboards to improve spatial analysis, fuel-consumption insights, and map-based storytelling beyond standard Power BI visuals.
Analyzed ChatGPT-related social media conversations using network analysis, sentiment analysis, named-entity recognition, and topic modeling.
Applied analytics for proactive infrastructure replacement, risk-aware prioritization, and long-term water-system planning.
Investigated machine-learning approaches for fraud classification using a high-dimensional dataset with more than one million records.
Exploratory data analysis of a credit-score classification dataset, focused on feature patterns, data quality, and model-readiness.