Researcher course in machine learning
Deep Learning for Finance
Deep learning for finance without the hype: neural networks from first principles, recurrent networks, convolutional and transformer models for prices, order books and fundamentals, trained and validated so that the results survive out of sample.
Deep learning for finance applies neural networks to prices, order books, fundamentals and text. It has produced real gains in some places and a great many false ones. This course teaches the models and, just as much, the validation that separates a result that will hold from one that will not.
Why do so many deep learning trading results fail?
Because financial data has a low signal-to-noise ratio, few independent observations and patterns that change over time. A large network will fit noise unless the data is prepared and tested with great care. Every model in the course is compared with a simple baseline on data it has never seen.
How is the course taught?
Audio lessons give the general subject, explainer films show networks learning and overfitting on market data, and the workbooks hold derivations, PyTorch notebooks and cheat sheets. Assignments and the project receive written feedback from the faculty.
Who is this course for?
Quants and data scientists who know classical machine learning and want to use neural networks responsibly. It counts toward the Certificate in Machine Learning for Trading and so toward the Fellowship in Computational Finance.
What you will be able to do
- Build and train feed-forward, recurrent, convolutional and transformer networks in PyTorch.
- Prepare financial data for deep models without look-ahead or leakage.
- Validate deep models with purged walk-forward tests and judge them against simple baselines.
- Decide when a deep model is worth its cost and when a linear or tree model is better.
Syllabus, module by module
Neural networks from first principles
Layers, activations, back-propagation, optimisers and regularisation.
Financial data for deep models
Scaling, sequences, labels, sample weights and the leaks that ruin results.
Sequence models
Recurrent networks, LSTMs and temporal convolutions for prices and volatility.
Transformers
Attention, time-series transformers and foundation models applied to markets.
Order books and cross-sections
Convolutional models of the book and networks for ranking many assets.
Does it beat the baseline?
Walk-forward tests, multiple-testing control and the cost of complexity.
How the certificate is earned
Graded assignments and a final project: a deep model for a return or volatility forecast, validated against baselines, with a written report on whether it adds value. On a pass you receive the Course certificate in Deep Learning for Finance, issued by the Institute with a verification code. Read how certification works.
Before you start
Financial machine learning at the Institute's level.
This course counts toward
- Certificate in Machine Learning for TradingOne semester of eight courses and a capstone on applying machine learning to markets without fooling yourself: labelling, features, purged validation, deep and language models, regimes and reinforcement learning.
- Fellowship in Computational FinanceThe top credential on the researcher path. Four semesters, 38 courses, and a dissertation supervised in writing and examined by two faculty members.
Questions applicants ask
Does deep learning work for stock prediction?
Sometimes, and far less often than published results suggest. Market data is noisy and scarce compared with images or text, so deep models overfit easily. The course teaches how to tell a real gain from a lucky one.
Which framework does the course use?
PyTorch, through notebooks in the workbook. The models are small enough to train on a laptop or a free cloud notebook.