// Teaching
Analytical excellence through challenge-driven education.
I teach across three disciplines, quantitative finance, analytics, and data science / AI, connecting rigorous theory with hands-on, production-minded practice. Each course’s description and learning outcomes are public; full syllabi are password-protected.
Finance
Introduction to Quantitative Finance
Fall · University (California)
Foundations of quantitative finance: time value of money, portfolio theory, the CAPM, fixed income, and an introduction to derivatives pricing, taught through Python notebooks on real market data.
Learning outcomes
- Build and evaluate mean-variance portfolios in Python
- Price options with binomial trees and Black-Scholes
- Reason quantitatively about risk and return
Machine Learning in Trading
Spring · University (California)
Applied machine learning for systematic strategies: feature engineering on market and alternative data, cross-validation that respects time, signal construction, and honest backtesting that survives transaction costs.
Learning outcomes
- Engineer leakage-free features from financial time series
- Backtest strategies with realistic costs and walk-forward validation
- Distinguish genuine signal from overfit noise
Generative AI in Finance
Spring · University (California)
How large language models, RAG, and agentic systems are applied in finance, research automation, document intelligence, and risk, with a hard focus on governance, evaluation, and human oversight.
Learning outcomes
- Design RAG systems over financial documents
- Evaluate LLM outputs for accuracy and risk
- Apply governance guardrails to AI in production
Analytics
Statistical Foundations for Analytics
Fall · University (California)
Probability, inference, and regression for decision-making, emphasizing causal reasoning, bias detection (Simpson’s paradox, survivorship), and the difference between correlation and real drivers.
Learning outcomes
- Run and interpret hypothesis tests and regressions
- Detect common statistical biases in real datasets
- Communicate uncertainty honestly to stakeholders
Predictive Modeling & Econometrics
Spring · University (California)
Econometric methods and predictive modeling for time series and panel data: ARIMA/GARCH, regularization, and model validation that holds up out of sample.
Learning outcomes
- Model volatility and trends in economic time series
- Select models with principled validation
- Avoid the most common forecasting pitfalls
Data Science & AI
Introduction to Data Science
Fall · University (California)
The end-to-end data-science workflow: problem framing, data wrangling with pandas, exploratory analysis, first models, and reproducible reporting, the habits that separate analysis from anecdote.
Learning outcomes
- Frame a business question as a data problem
- Wrangle and explore data reproducibly in Python
- Build and communicate a first predictive model
Machine Learning Fundamentals
Spring · University (California)
Supervised and unsupervised learning from the ground up: the bias-variance tradeoff, regularization, ensembles, and model selection, with an engineering eye toward deployment.
Learning outcomes
- Train, tune, and evaluate core ML models
- Reason about the bias-variance tradeoff
- Prepare models for reliable deployment
Deep Learning & NLP
Fall · University (California)
Neural networks in practice: CNNs, RNNs, and transformers; representation learning; and modern NLP, from embeddings to attention, built and trained in PyTorch.
Learning outcomes
- Implement and train deep networks in PyTorch
- Apply transformers to language tasks
- Diagnose and fix training pathologies
// For programs & students
Looking for a guest lecture or workshop?
I design and deliver applied courses on AI and quantitative finance.