Quantitative Trading

Quantitative trading is a research discipline before it is a trading activity. Most of the work is deciding which ideas deserve testing, testing them without fooling yourself, and turning the survivors into positions that can actually be traded.

How do quant traders find strategies?

They start from a reason. A strategy that works because someone is paid to take a risk, or because a group of investors acts predictably, or because a market structure creates a flow, is more likely to keep working than one found by searching through indicators. The course begins with the reason and treats data mining as the danger it is.

Why does the course give so much time to costs and capacity?

Because a signal with a strong backtest can be worthless after costs, and a strategy that works with a small account can fail at a size that matters. Estimating both early saves months of work on ideas that cannot pay.

Who is this course for?

Analysts and traders who want the full research process, and students heading for quant research roles. It counts toward the Certificate in Algorithmic Trading and the Professional Diploma in Algorithmic Trading.

What you will be able to do

• Write a trading hypothesis with an economic reason and a testable prediction.
• Build, normalise and combine signals across a universe of instruments.
• Turn signals into positions with risk targeting and constraints.
• Estimate transaction costs and strategy capacity.
• Decide, with stated criteria, whether a strategy should go forward.

Syllabus, module by module

1. Hypotheses and edges

   Risk premia, behavioural effects and structural flows; why an edge exists and who pays for it.

2. Signals

   Raw features, normalisation, ranking, decay and the information coefficient.

3. Time series and cross-section

   Trading one asset against its own past versus ranking many assets against each other.

4. Combining signals

   Equal weights, regression weights and why simple combinations often win out of sample.

5. From signals to positions

   Volatility targeting, neutrality constraints, turnover limits and rebalancing.

6. Costs and capacity

   Spread, impact models, borrowing, and how much capital a strategy can take.

7. Is it real?

   Multiple testing, deflated Sharpe ratios, subperiod stability and decision criteria.

8. The research note

   Writing up a strategy so a reviewer can reproduce and challenge it.

9. Project lab

   Supervised work on the assessed research project.

How the certificate is earned

An assessed project: you take one hypothesis from idea to a tested cross-sectional or time-series strategy with costs, and submit the code and a research note in the form a quant desk would expect. On a pass you receive the Course certificate in Quantitative Trading, issued by the Institute with a verification code. Read how certification works.

Before you start

Statistics to regression level, working Python with pandas, and the basics of backtesting.

• Statistics for Finance and Trading
• Algorithmic Trading Foundations