Get Started for Free →
Learn Programs Library About Us Contact Get Started for Free →
Requires: Python Fundamentals
Self-paced course · Intermediate

Applied
Machine Learning.

Build real ML models on real financial data with scikit-learn. Two full case studies, from raw data to a production model you can explain to your team.

4.9average student rating
3.5 hours of video
7 modules
2 real case studies
Certification exam
Lifetime access
$199one-time
30-day money-back guarantee. No questions asked.
liquidity_model.pyPYTHON 3.11
# Build a GradientBoosting pipeline
from sklearn.pipeline import Pipeline
from sklearn.ensemble import GradientBoostingRegressor
pipe = Pipeline([
("scaler", StandardScaler()),
("model", GradientBoostingRegressor()),
])
pipe.fit(X_train, y_train)
Model Evaluation · R-squared
Elastic Net0.847
Random Forest0.891
Gradient Boost0.923BEST
4.95
10,000+ students trained
BMO
J.P. Morgan
RBC
TD
BMO
J.P. Morgan
RBC
TD
BMO
J.P. Morgan
RBC
TD
*These banks have used one or more PyFi products to train their employees
What you'll build

What you will build by the end.

Two production-grade case studies on real financial data. Models you can explain to your team, built with the same open-source tools the industry runs on.

Clean and explore real financial datasets: handle missing values, detect outliers, and visualize distributions before a single model is trained
Build and compare regression models, Linear, Ridge, Lasso, and Elastic Net, and know when each one wins
Build a bond liquidity regressor on real data with scikit-learn pipelines, and ship the best of five models
Build classification models: Logistic Regression, Random Forest, and Gradient Boosting
Build an investor classifier and evaluate it with confusion matrices, AUROC, and F1 scores
Tune and validate models with cross-validation and GridSearchCV, then select the winner
Read and explain the metrics (R-squared, AUROC, F1) to your team with confidence
Earn the PyFi machine learning certification for your resume and LinkedIn
Curriculum

7 modules. 3.5 hours. Two case studies.

Click any module to preview lessons.
03.01Feature engineering for liquidity prediction
03.02Building and comparing regression pipelines
03.03Model selection and final evaluation
The ML pipeline

Four steps. Every project.

01

Prepare Your Data

Load, clean, handle missing values. The foundation everything else depends on.

02

Build Your Pipelines

Combine preprocessing and models into reproducible sklearn pipelines.

03

Train & Tune

Fit models. Cross-validate. Grid-search hyperparameters.

04

Select the Winner

Compare metrics. Pick the best model. Export for production.

Sample lesson · watch before you buy
liquidity.csv
spreadvolumey
0.421.2M0.81
0.380.9M0.76
0.512.1M0.88
0.290.7M0.69
train_test_splittest_size = 0.2
Train
641 rows · 80%
Test
161 rows · 20%
Watch a free lesson
Free sample lesson
Case study · sklearn·Splitting data with train_test_split()
Is this for you?

This course is for you if...

  • You have basic Python skills (variables, pandas, NumPy).
  • You want to apply ML to real finance problems.
  • You work in investment banking, equity research, risk, or portfolio management.
  • You want to understand the ML models your quant team builds.

This course is not for you if...

Your instructor
Zach Washam

Zach Washam
Ex - Wells Fargo

Zach founded PyFi (originally Machine Learning Edge) in 2018 after a career at Wells Fargo Securities. While working as an analyst on the debt syndication desk, he taught himself Python and built the firm's first machine learning algorithm for investment banking, using predictive modelling to improve decision-making in capital markets.

He submitted two algorithms for patent protection and won Wells Fargo's 2018 Local Sphere Innovation Award. His original research, including the efficient frontier framework for mapping Python against competing finance tools, remains foundational to PyFi's published work. His courses have been delivered to thousands of finance professionals at institutions including J.P. Morgan, Royal Bank of Canada, Bank of Montreal, and TD Bank.

Ex Wells Fargo Securities
Built WFS's first ML algorithm for investment banking
2018 Local Sphere Innovation Award
Taught thousands of finance professionals
Reviews

What finance professionals say.

Real reviews from finance professionals who have learned Python and machine learning with PyFi.

NI
Naquan Ishman
Principal
Highly Recommend!
What an excellent course. The Python portion gets you quickly up to speed on Python data structures, common libraries, and functions. The ML portion gives two end to end examples of structuring, training, testing, and selecting ML models. The pace of the demo and level of detail given were great.
FM
Franklin Monzon
Finance & Engineering Student
Python Fundamentals / Python Applied ML
As a Finance student, we're always looking for ways to set ourselves apart in the space. I found that PyFi not only taught me the fundamentals of Python but also gave me a practical view of how Python and machine learning can be applied to real financial problems.
AI
Andre Irving
CFO
Live Python Class: 5 Stars!
Just finished the PyFi course and I can't recommend it enough! Four days, two hours a day — and every minute was worth it. The live instructors were fantastic: helpful, engaging, and clearly passionate about the material. They made Python feel approachable even for someone just starting out. What I loved most was how the course connected coding concepts directly to real finance scenarios, so you could immediately see the value of what you were learning. If you're in finance and have been thinking about picking up Python, stop thinking and just sign up. PyFi is the real deal!
JG
Jacob G.
FP&A Manager
Introduction to Python Course
The Introduction to Python course was a great start on the basics of Python. Zach was great at answering questions and taking the class along the journey to build a strong foundation of Python knowledge. This has me excited to continue learning more Python and applying it to my everyday work. I'll be recommending this to my team members in FP&A.
Enroll

Start building ML models for Finance today

Applied Machine Learning

4.9out of 5
$199.00 USD
Enroll me now

Join over 10,000 professionals in the finance function from analysts, associates, VPs of investments, and CFOs, including top banks like JP Morgan, TD Bank, Bank of Montreal, and Royal Bank of Canada who have used PyFi to keep their skills ready for the future of finance.

What you're getting
Trusted by Top Global Banks
Award-Winning Algorithms
Instructor Support
Elite Professional Training
99% Satisfaction Rate
30-day Money Back Guarantee

Questions? Email support@pyfi.com

Risk reversal

The risk is 100% on us.

Work through both case studies and every module. If you do not feel more capable building machine learning models in Python within 30 days, email us and we will refund every cent, no forms and no hoops. The lessons and your code notebooks stay yours either way.

Umut Sagir
CTO · Head of Programming
support@pyfi.com
30-day money-back guarantee, no questions asked
Keep the course and every code notebook, even if you refund
Lifetime access, including all future updates
Real instructor support in the lesson comments
Bundle and save

Bundle & Save.

Pair Applied Machine Learning with the fundamentals and pay far less than their combined retail value.

1
2
2 courses
Bundle

Machine Learning Edge Bundle

Python Fundamentals plus Applied Machine Learning, with both certifications.

Python Fundamentals
Applied Machine Learning
Both certifications + lifetime access
$249$298Save $49 · 16% off
Get the bundle
Questions

Frequently asked questions.

Yes. You should be comfortable with Python basics, pandas, and NumPy. If you are starting from zero, take Python Fundamentals first.

Build models, not just spreadsheets.

$199 one-time·Lifetime access·30-day money-back