Machine Learning
From "what is machine learning?" to walk-forward backtests. Features, regression, classification, ensembles and portfolio optimisation - applied to financial markets with the out-of-sample discipline real quants live by.
Recommended first: Python Foundations · Pandas: DataFrames and returns
Curriculum
Module 1: ML Foundations
0/2Fit, predict, evaluate - and the overfitting trap every quant must escape.
Module 2: Feature Engineering
0/1Build predictive features from raw price data.
Module 3: Linear Regression
0/1Train and evaluate a return prediction model.
Module 4: Backtesting
0/1Evaluate strategy performance with walk-forward testing.
Module 5: Portfolio Optimisation
0/1Markowitz mean-variance optimisation.
Module 6: Classification
0/2Predict market direction with logistic regression.
Module 7: Ensemble Methods
0/1Reduce overfitting with Random Forest and feature importance.
Build it for real: Colab + MLflow
Graduate from the browser: a ready-to-run Colab notebook that pulls real market data, engineers leak-free features, trains two models, and tracks every experiment with MLflow - a workflow you can reuse for your dissertation.
Download the notebookOpen Google Colab → File → Upload notebookCertificate of Completion
Finish all 9 lessons to earn a Machine Learning certificate you can add to your LinkedIn and CV.
What You'll Be Able To Do
- Build and backtest ML trading strategies
- Apply classification to credit/risk problems
- Present models in professional reports