|Prerequisites||CS983 – Evolutionary Computation for Finance 1|
|Availability||Available only to MSc Quantitative Finance students|
|Contact||Lectures: 5 | Labs: 15 | Homework / Private Study: 80|
|Assessment||Individual assignments (50%), and a one-hour examination (50%)|
|Resit||By examination (1-hour)|
|Lecturer||Dr Marc Roper|
This class aims to build on the foundations CS983 – Evolutionary Computation for Finance 1 – to explore more advanced applications of evolutionary and natural computing, in particular algorithmic trading.
The course is very practical in its nature: much of the learning is achieved via an assessed mini-projects, and students are expected to develop a solutions to problems using neural networks and evolutionary computation techniques, evaluate these on real data sets, and compare them with other more traditional approaches. Consequently, a large amount of self-directed study and learning is expected.
After completing this class participants will be able to:
- Understand the benefits and opportunities for evolutionary computing in the context of financial applications;
- Understand the principles of evolutionary computation: genetic programming and genetic algorithms in particular, and also neural networks;
- Understand how the computational approaches covered in the class may be applied to financial problem solving and understand their limitations;
- Develop and evaluate practical solutions to finance-based problems.
- Advanced Neural Network configurations (e.g. RNNs and LSTMs);
- Algorithmic Trading – This topic looks at the application of both Neural Networks potentially combined with GAs or GP to identify automatically at what point a trade should be executed, and evaluate the effectiveness of the strategy through backtesting.