Machine Learning for Financial Modeling
Financial markets generate massive amounts of data every day. But raw numbers don't tell the whole story. We built this program to help professionals bridge the gap between traditional financial analysis and modern machine learning techniques.
Over the past three years, we've worked with analysts who needed practical skills—not just theory. They wanted to understand how algorithms could improve risk assessment, spot market patterns, and build better forecasting models. That's what this program delivers.
Bryn Hartsfield
Lead Instructor
Bryn spent a decade analyzing credit risk at regional banks before transitioning to data science. He teaches the practical side of model validation.
Davor Ljungqvist
Technical Advisor
Davor builds algorithmic trading systems. His approach focuses on what actually works in production, not what looks good on paper.
What You'll Learn
Curriculum Built Around Real Financial Problems
Foundation Building
Start with Python fundamentals and statistical concepts. We cover regression analysis, probability distributions, and how to clean messy financial datasets. Most people underestimate how much time they'll spend cleaning data—it's usually about 60% of any project.
Topics: Python basics, pandas, NumPy, statistical inference, data preprocessing
Supervised Learning Applications
Learn classification and regression techniques that actually matter in finance. We focus on credit scoring models, default prediction, and portfolio optimization. You'll build models using real historical data from emerging markets.
Topics: linear models, decision trees, random forests, gradient boosting, model evaluation
Time Series and Forecasting
Financial data has temporal dependencies that standard models ignore. You'll work with ARIMA, GARCH models, and LSTM networks to forecast volatility and price movements. This phase includes backtesting strategies and understanding when models break down.
Topics: time series decomposition, ARIMA, volatility modeling, recurrent neural networks
Deployment and Risk Management
Building a model is one thing. Deploying it responsibly is another. We cover model validation, stress testing, and how to communicate results to non-technical stakeholders. You'll also learn when not to use machine learning.
Topics: model validation, backtesting, risk metrics, API development, monitoring
How We Approach Learning
We've refined our teaching method based on feedback from over 200 professionals who've completed the program. Here's what matters most to people building real financial models.
Case-Based Projects
Every module includes projects based on actual financial scenarios from Vietnam's banking sector. You'll work with local market data, deal with currency volatility, and handle regulatory constraints that textbooks don't cover.
Small Cohorts
We cap each cohort at 18 participants. This isn't arbitrary—it's the maximum size where everyone can present their work and get meaningful feedback. Larger groups become lectures, and that's not what we're doing here.
Flexible Pacing
Most participants have full-time jobs. The program runs over six months with self-paced modules and bi-weekly live sessions. If you need to skip a session, recordings and materials stay accessible for 12 months after completion.
Program Timeline
The next cohort launches in October 2025. Here's how the six months typically unfold for participants who stay on the recommended schedule.
Foundation Phase
Python programming and statistical methods. Weekly exercises with financial datasets from emerging markets.
8 weeks
Core Modeling
Build supervised learning models for credit risk and portfolio optimization using real bank data.
8 weeks
Advanced Topics
Time series forecasting, volatility modeling, and neural networks for sequential financial data.
6 weeks
Capstone Project
Design and validate a complete financial model addressing a problem relevant to your work.
4 weeks