Projects

This project combined supervised machine learning with profit-aware pricing optimization. Customer acceptance probabilities were modeled from financial, mortgage and behavioral characteristics, then used to evaluate alternative renewal rates at the individual customer level. The framework connected predictive outputs to pricing decisions rather than treating model prediction as the final objective.

This project implemented an end-to-end financial market data lakehouse using Python and PySpark. Market data moves through Bronze, Silver and Gold layers, with each stage adding structure, validation and analytical features. The architecture separates data engineering from downstream analysis so the Gold layer can serve as a reusable foundation for multiple analytical datasets.

The project uses a deliberately narrow agentic architecture centered on research orchestration. A locally hosted Qwen3:30b model interprets a research question, selects from complementary research tools, synthesizes the retrieved information and returns a validated structured response. The constrained scope is intentional: limiting the agent's responsibility creates a simpler and more testable foundation for exploring agentic AI development before introducing more complex capabilities.

This project evaluated CNN-RNN architectures that combine a frozen ResNet18 backbone for spatial feature extraction with LSTM, GRU and bidirectional GRU networks for modeling movement across video sequences. Each architecture received the same frame-level feature representations and experimental conditions, allowing the comparison to focus on differences in temporal sequence modeling.

This project combined stylometric analysis with supervised machine learning to distinguish the writing styles of James Madison and Alexander Hamilton. Linguistic characteristics were engineered as interpretable features, while TF-IDF representations captured patterns in word usage. Multiple classification models were then evaluated using known-authorship papers before being applied to the disputed essays.

This project transformed historical Men's 50-yard freestyle results into a structured analytical dataset through automated document parsing, data cleaning and normalization. Statistical analysis and visualization were then applied to examine changes in performance over time, program-level success, competitive distributions and exceptional individual performances.

This project designed and implemented a normalized SQL Server database to represent the game world, manage relationships between entities and enforce gameplay rules. Stored procedures exposed gameplay operations while database triggers handled validation and audit logging, creating a database-driven backend for the text-based adventure.

I designed the portfolio as a content-driven Astro application, separating structured project content from presentation through Astro content collections, reusable components and schema validation. The project architecture allows different types of technical work to share a consistent presentation while selectively exposing the sections relevant to each project. The visual system emphasizes restrained design, responsive layouts, technical diagrams and concise project narratives.