Hi, I’m Bryan. I’m a data scientist with an experienced background in IT. I use science to help understand complex, human-centered problems.

This site reflects how I use data, the scientific method, and humanist values to help make the world a better place.

Three Pillars

Logo

Electronics

Electronics

  • Sensors and Sensor Circuit Design – thermal sensors, sensor development and prototyping, thermistors, RTDs and thermocouples
  • Statistical inference – estimation, hypothesis testing, confidence intervals
  • Regression & classification – linear and logistic models, interpretability
  • Model evaluation – bias–variance tradeoff, ROC, precision–recall, calibration
  • Experimental design & causality – A/B testing, confounding, observational analysis
  • Data quality & cleaning – missing data, outliers, validation rules
  • Feature engineering – transformations, scaling, domain-informed features
  • Exploratory Data Analysis (EDA) – statistical summaries and visual pattern discovery
  • Uncertainty & reliability – error analysis, robustness, reproducibility

Development

Modeling & Algorithms

  • Supervised learning – regression, classification, training workflows
  • Unsupervised learning – clustering, dimensionality reduction
  • Tree-based models – Random Forests, Gradient Boosting
  • Model selection & tuning – cross-validation, hyperparameter search
  • Optimization – gradient descent, loss functions, convergence
  • Deep learning foundations – neural networks, representation learning
  • Algorithmic thinking – abstraction, decomposition, solution design
  • Computational complexity – scalability and performance tradeoffs
  • Data structures – trees, graphs, hashing, indexing
  • End-to-end ML pipelines – from problem formulation to trained models

Integration

Delivery & Human Context

  • SQL & relational modeling – schema design, joins, indexing
  • Data pipelines – ETL, reproducible workflows, automation
  • Version control – Git, GitHub, collaboration workflows
  • Data visualization – storytelling, dashboards, insight communication
  • Ethics & fairness – bias, privacy, responsible data use
  • Interpretability – explainable models, transparent reporting
  • Stakeholder communication – translating technical results
  • Deployment awareness – APIs, cloud basics, static & model hosting
  • Documentation – READMEs, notebooks, technical writing
  • End-to-end system integration – connecting data, models, and people