Open course in machine learning
AI Trading: What Works and What Does Not
A sober introduction to artificial intelligence in trading: where machine learning is used by professional firms, why most AI trading claims fail on inspection, the specific traps of financial data, and how to judge a strategy or product that says it uses AI.
Artificial intelligence in trading is surrounded by more claims than evidence. Professional trading firms do use machine learning, and some use it extensively. Most products marketed to individuals as AI trading systems, though, rest on backtests that would not survive a careful look. This free course explains the difference.
Can artificial intelligence really trade the markets profitably?
In some uses, yes. Machine learning is applied to execution, to forecasting quantities such as volume and volatility, to extracting information from text, and to combining many weak signals into one. Those uses share a feature: large amounts of data and a well-defined target. Predicting the direction of prices days ahead with a single model has neither, and results there are much weaker.
Why do so many AI trading strategies fail?
Financial data is noisy, the number of truly independent observations is small, and markets change. A flexible model can fit the past almost perfectly and learn nothing useful. Add look-ahead errors and ignored trading costs, and a backtest can show large profits from a strategy that will lose money. The course shows each failure with examples.
Where does this course lead?
It is the free starting point of the machine learning track. Machine Learning for Trading is the next step, followed by the researcher-level Financial Machine Learning and Reinforcement Learning for Trading.
What you will be able to do
- Describe where machine learning is used in professional trading.
- Explain why financial data is hard for machine learning.
- Recognise overfitting and look-ahead bias in AI trading claims.
- Ask the questions that test whether an AI trading product is credible.
Syllabus, module by module
What AI means in trading
Machine learning, deep learning and language models, and the jobs each is used for.
Where it works
Execution, forecasting volume and risk, processing text and data, and combining many weak signals.
Why it often fails
Noisy data, few independent observations, changing markets and overfitting.
Judging the claims
Backtests, live records, costs and the questions to ask before trusting an AI trading product.
How the certificate is earned
Self-check questions at the end of each lesson. The course is not assessed. Completing every lesson earns a Certificate of attendance, which states that the course is not assessed. Read how certification works.
Questions applicants ask
Do AI trading bots work?
Most retail AI trading products show backtests rather than audited live records, and backtests are easy to overfit. Professional firms do use machine learning, but mainly as one part of a carefully tested process, not as a standalone bot. The course explains how to tell the difference.
Can ChatGPT predict stock prices?
General language models are not built to forecast prices and have no reliable edge at it on their own. Language models are useful in trading for reading and summarising text, such as news and filings, which is a different task.
What should I take next?
Python for Finance and Statistics for Finance, then Machine Learning for Trading, which teaches the methods with the safeguards this course describes.