Postgraduate Course: Financial Machine Learning (CMSE11475)
Course Outline
| School | Business School |
College | College of Arts, Humanities and Social Sciences |
| Credit level (Normal year taken) | SCQF Level 11 (Postgraduate) |
Availability | Not available to visiting students |
| SCQF Credits | 10 |
ECTS Credits | 5 |
| Summary | This course provides a complete and systematic overview of machine learning methods on finance and investment, including financial data structure and feature engineering; investment strategy and portfolio allocation; back-testing statistics. |
| Course description |
Academic Description:
Machine learning is changing all aspects of our lives and has been adopted in finance area as a disruptive technology that may lead to profound changes in how everyone invests and manages the risks in the future. Many financial institutions, including huge investment banks on sell-side, cutting-edge hedge funds on buy-side and leading consulting firms, have heavily invested in this machine learning techniques in finance.
Whether we use support vector machine, random forest, AdaBoost, convolutional neural network, and so on, there are many shared generic problems we will face: data structuring, labelling, weighting, stationary transformations, cross-validation, feature selection, feature importance, investment strategy, overfitting, and back testing. In the context of financial modelling, answering these questions is non-trivial, and framework-specific approaches need to be developed. That's the focus of this course.
This course aims to provide a complete and systematic treatment of machine learning methods specific for finance. It contains four primary parts:
- An introduction of deep neural network;
- Financial data structure and feature engineering;
- Investment strategy and portfolio allocation;
- Back-testing statistics.
On the finance side, this course will enable students to understand the structures of different financial data, transformation of raw data into informative signals and further into actual investment algorithms, the evaluation of the profitability of investment strategy under various scenarios, and the economic mechanism of the profit or loss. On the technical side, it equips the student with capability to correctly use machine learning method on identifying true discovery of profitable investment opportunity and to use R (or Python/MATLAB) to implement the strategy code and further deploy it into the production line.
Student Learning Experience:
Tutorial/seminar hours represent the minimum total live hours - online or in-person - a student can expect to receive on this course. These hours may be delivered in tutorial/seminar, lecture, workshop or other interactive whole class or small group format. These live hours may be supplemented by pre-recorded lecture material for students to engage with asynchronously.
|
Entry Requirements (not applicable to Visiting Students)
| Pre-requisites |
|
Co-requisites | It is RECOMMENDED that students also take
Data Mining 1 (CMSE11459) AND
|
| Prohibited Combinations | |
Other requirements | Course only open to MSc Finance, Technology and Policy & MSc Banking & Risk students. MSc Banking & Risk students must have taken Data Mining 1 CMSE11459 |
Course Delivery Information
|
| Academic year 2021/22, Not available to visiting students (SS1)
|
Quota: 46 |
| Course Start |
Semester 2 |
Timetable |
Timetable |
| Learning and Teaching activities (Further Info) |
Total Hours:
100
(
Seminar/Tutorial Hours 10,
Programme Level Learning and Teaching Hours 2,
Directed Learning and Independent Learning Hours
88 )
|
| Additional Information (Learning and Teaching) |
Seminar/Tutorial hrs are the min total live hrs, online or in-person, students can expect to receive
|
| Assessment (Further Info) |
Written Exam
0 %,
Coursework
100 %,
Practical Exam
0 %
|
| Additional Information (Assessment) |
50% coursework (group) - assesses course Learning Outcomes 1, 2, 3
50% coursework (group) - assesses course Learning Outcomes 3, 4
|
| Feedback |
Not entered |
| No Exam Information |
Learning Outcomes
On completion of this course, the student will be able to:
- Apply the knowledge of financial theories and skills of pre-processing the financial data to construct useful features for machine learning methods.
- Transform the constructed financial features into informative investment signals with predictive powers.
- Transform the informative features into the actual profitable investment strategy with formulated theory that explains and backs the theory as a ¿white box¿.
- Understand the importance of the back-testing and the over-fitting, and be able to assess the profitability of an investment strategy under various scenarios.
|
Reading List
Advances in Financial Machine Learning, ISBN: 978-1-119-48210-9
Machine Learning in Finance: From Theory to Practice, ISBN : 3-030-41068-4
Deep Learning, ISBN : 9780262035613 (hardback) |
Additional Information
| Graduate Attributes and Skills |
Research & Enquiry:
On completion of the course, students should be able to:
- Understand the types of financial data and the initial pre-processing of the raw data
- Understand the financial features and the economic mechanism of the features
- Understand how to use machine learning on portfolio allocation with model parameter tuned by cross-validation
- Understand the importance of back-testing to the investment strategy and the methods of back-testing
Personal & Intellectual Autonomy:
On completion of the course, students should be able to:
- Applying relevant techniques and specific knowledge to design, implement, deploy and evaluate machine learning based portfolio allocation strategy
-Recognize profitability and potential risks of different strategy by using different back-testing methods
Communication skills
On completion of the course, students should be able to:
- Use state-of-the-art machine learning method to develop quantitative investment strategies
- Be capable of cooperating with risk analyst and regulatory team with respect to the evaluation of potential risk of strategies
|
| Keywords | Not entered |
Contacts
| Course organiser | Dr Yi Cao
Tel: (0131 6)51 5338
Email: Yi.Cao@ed.ac.uk |
Course secretary | Mrs Kelly-Ann De Wet
Tel: (0131 6)50 8071
Email: K.deWet@ed.ac.uk |
|
|
University Homepage