I build interpretable machine learning systems, automate complex workflows, and apply rigorous quantitative methods to financial and engineering problems. My work blends statistical learning, computational modeling, and transparent software design. I also bring a decade of industry experience leading analytics teams, developing predictive models, and delivering enterprise-scale reporting solutions that drive strategic decision-making.
- Machine learning for options volatility modeling
- Interpretable ML and model diagnostics
- Large-scale data engineering and workflow automation
- Unsupervised learning research (PCA, KPCA, SVD, EM, Kernel K-Means)
- Business intelligence systems and predictive analytics for operational efficiency
Languages: Python, R, SQL
ML / Stats: scikit-learn, PyTorch, NumPy, SciPy, statsmodels
Data Engineering: Pandas, Polars, Spark, Airflow, Google BigQuery
Automation: PowerShell, REST APIs, cloud workflow orchestration
Visualization: Tableau, R Shiny, Google Data Studio, Matplotlib, Seaborn, Plotly
Platforms: Google Workspace, Oracle, MS Access
- Directed development of enterprise dashboards, reducing latency by 35% and enabling real-time KPI monitoring
- Built predictive models and data quality frameworks improving accuracy across 200+ customer-facing reports
- Collaborated with engineering teams to enhance database architecture and conduct quality assurance audits
- Mentored analysts on SQL optimization, visualization best practices, and stakeholder communication
- Managed analytics projects processing 2M+ student records annually
- Designed dashboards and reporting tools for university administration
- Built R Shiny and Google Data Studio solutions integrating enrollment, call center, and financial aid data
- Developed an NLP-based candidate evaluation system reducing hiring evaluation time by 40%
- Evaluated regulatory changes and emerging financial technologies for institutional adoption
- Oversaw facilities inventory database covering 1,700+ properties and 22M sq. ft.
- Redesigned annual reporting processes, achieving a 50% reduction in processing time
- Built MS Access–Oracle integration improving data integrity by 25%
Dimensionality reduction and clustering on mice protein expression data using PCA, KPCA, SVD, K-Means, Kernel K-Means, and EM. Emphasis on interpretability and diagnostic clarity.
Machine learning–driven volatility surface estimation with a focus on stability, interpretability, and model transparency.
Automated loan optimization and eligibility analysis using reproducible, auditable computational workflows.
PowerShell + Python systems with explicit logging, version checks, and transparent error handling to maximize trust and reproducibility.
I value clarity, reproducibility, and interpretability. Whether modeling volatility, designing automation pipelines, or building enterprise analytics systems, I aim to create solutions that are technically rigorous, transparent, and easy to reason about.
- PhD Candidate — Computer Science, Florida Atlantic University
- MIT — Full Stack Development, University of Georgia
- MBA — MIS, Monmouth University
- BBA — Finance, University of Texas at Austin
- GitHub: https://github.com/UTexas80