Learning Goals Aligned with Professional Profile:
The goal of this class is to provide students with a strong foundation in algorithmic trading as well as the tools and techniques used in the industry. The class will cover everything from basic programming concepts to advanced trading strategies and methods for research into new alpha sources. Students will have the opportunity to apply what they learn in hands-on projects throughout the course.
This course is an up-to-date version of the course, Algorithmic Trading Strategies. Nick taught a version of this course at University College London, to Computational Finance and Risk Management PhD and MSc students from 2015 – 2023, and online through QuantsHub and other platforms. With over 500 students having successfully completed earlier versions of this course, and the curriculum continually being re-jigged, it seemed an appropriate time for a larger update to broaden the perspective and make the course more applied, with the goal of having students be able to implement methods, models and frameworks themselves. Changes to previous courses include:
- In addition to looking at the returns of QIS, Risk-premia or Factor-based strategies (e.g., trend-following, carry, etc and equities momentum, value, etc factors), this course explicitly considers larger returns-forecasting models and the value of including factors as exogenous features.
- While including much of the university course material, this course goes beyond the merely academic to focus on practical implementations. The academic literature is of interest only in that we can use it as a starting point for delving deeper into real-world applications.
- We expect a working knowledge of programming and can focus more on greater value added material
Unlike the earlier courses, the new Algorithmic Trading: Practitioners Guide course takes a hands-on approach to building trading pipelines, from data to features to modelling to allocation to execution to performance measurement, guiding the student through common practice as well as areas of innovation. It is designed to go far beyond the purely academic remit of the UCL course and the more practical online course.
Prerequisites – Goals of Class
- Provide a strong foundation in the tools and techniques used in algorithmic trading.
- Cover everything from basic programming concepts to advanced trading strategies and methods for research into new alpha sources.
- Apply everything in hands-on projects throughout the course.
- Intermediate or Experienced Programmer – preferably with working knowledge of Python – all examples in the class will be in Python, in Jupyter Notebooks, using Numpy and Pandas. While other languages may be considerably faster and more stable, Python is particularly noted for the speed of development, the access to a wide range of libraries (stats or ML-stack), and interoperability with other languages. Python also is a noted teaching language and a vast number of students have been educated in Python.
- Statistics or Econometrics or (Statistical) Machine Learning – We will assume strong familiarity with a lot of statistical concepts, although there will be some review of Time Series Econometrics (e.g., ARIMA models and concepts of stationarity). Understandings of basic distributions, statistical hypothesis testing and OLS will be a bare minimum.
- Basic Finance and familiarity with Economics – We will assume a basic knowledge of financial markets. Our focus will be markets which are less model-dependent (i.e., less Fixed Income and Vol, more FX, Equities, Futures), although there will be illustrations from each. We will also assume a basic understanding of utility theory from Economics. And Economics impacts all markets and knowing this will take the student a long way.
- A plus: Some familiarity with SDEs (e.g., as in Black-Scholes), and differential equations.
This course is for:
Discretionary Traders / Risk Managers – Understand the mechanics of the market and develop the tools to devise and manage new and improved algorithmic strategies of different types including multi-asset strategies. Learn the importance of allocation frameworks, execution models and performance testing. Recognise pros and cons of various approaches to designing strategies and the common pitfalls encountered by algorithmic traders.
Algorithmic Traders / Quants – Appreciate when commonly-used strategies work and when they don’t. Understand the statistical properties of strategies and discern the mathematically proven from the empirical. Expand your technology toolkit to incorporate the latest techniques including open-source tools and models from other areas of the quant industry.
Academics / Students / Data Scientists – Gain familiarity with the broad area of algorithmic trading strategies. Master the underlying theory and mechanics behind the most common strategies. Acquire a solid understanding of the principals and context necessary for new academic research into the large number of open questions in the area.
Download Event PDF