Postgraduate Course: Pattern Recognition in Financial Data (CMSE11527)
Course Outline
| School | Business School |
College | College of Arts, Humanities and Social Sciences |
| Credit level (Normal year taken) | SCQF Level 11 (Postgraduate) |
Availability | Available to all students |
| SCQF Credits | 20 |
ECTS Credits | 10 |
| Summary | The study of Artificial Intelligence and the development of tools aimed at analysing data from the many and growing data sources requires generating a systematic understanding of how we can learn from data. A principled approach to this problem is critical given the wide differences in the places these methods need to be used. There is no sector where this need is more obvious than in the financial services sector, where the provision of new consumer financial products requires a detailed understanding of consumer behaviour and needs. Financial services companies can develop an understanding of the data generating processes relevant to their product development and services delivery activities by generating algorithms that recognises patterns, for example, at cohort or societal levels. This course is an advanced offering to help students develop further skills in the intelligent utilisation of machine learning methods in the context consumer finance data, such as open banking datasets. A key offering of this course is that students will be able to gain an understanding of how to adapt methods to fit problems rather than simply applying existing techniques to problems. |
| Course description |
This course is for students who want to research and develop machine learning methods in the future. While other courses might focus more on using machine learning methods, this course helps students develop skills needed for designing new machine learning methods tailored to use with financial and economic data. It is also designed to be in a constant state of evolution; hence, the precise set of methods and algorithms employed in illustrating and exploring crucial concepts will undergo modifications from year to year.
Content Outline:
-Review of classification and gradient-based fitting
-Expanded feature representations (e.g., basis functions, neural networks and kernel methods)
-Generalization, regularization and inference (e.g., penalized cost functions, Bayesian prediction, learning theory)
-Model selection, pruning and combination (e.g., cross-validation, Bayesian methods, sparsifying regularisers, ensemble methods)
-Representation and metric learning (e.g., dimensionality reduction, clustering, feature learning)
-Optimization and Inference algorithms (e.g., stochastic gradient descent, simple Monte Carlo ideas, and more specialized methods as required)
-Formulating problems as machine learning-relevant and adapting methods to fit problems
-Ethical issues, such as responsible application of methods and privacy concerns
|
Entry Requirements (not applicable to Visiting Students)
| Pre-requisites |
It is RECOMMENDED that students have passed
Python Programming (MATH11199)
|
Co-requisites | Students MUST also take:
Introductory Applied Machine Learning (Semester 2) (INFR11205)
|
| Prohibited Combinations | |
Other requirements | This course involves the mathematical application of algebra, vectors and matrices, calculus, probability, and problem solving. As an example, students will need to be able to differentiate linear algebra expressions with respect to vectors, interpret inner-products and quadratic forms geometrically, and compute expectations of linear algebra expressions under simple distributions. Some of the required details can be learned during the course, and pre-joining materials for the MSc Finance, Technology & Policy also includes useful study guides. However, practical mathematical skills typically take time to acquire. Practical exercises will also require the use of named programming languages, such as Python. Therefore, programming experience is vital for course enrolment. |
Information for Visiting Students
| Pre-requisites | None |
Course Delivery Information
|
| Academic year 2022/23, Available to all students (SV1)
|
Quota: None |
| Course Start |
Semester 2 |
Timetable |
Timetable |
| Learning and Teaching activities (Further Info) |
Total Hours:
200
(
Lecture Hours 20,
Summative Assessment Hours 3,
Programme Level Learning and Teaching Hours 4,
Directed Learning and Independent Learning Hours
173 )
|
| Assessment (Further Info) |
Written Exam
50 %,
Coursework
50 %,
Practical Exam
0 %
|
| Additional Information (Assessment) |
50% coursework (individual) - assesses all course Learning Outcomes
50% exam (individual) - assesses course Learning Outcomes 1, 2, 5 |
| Feedback |
Formative: will be provided on an ongoing basis through class discussions.
Summative: students will be provided with individual feedback for the coursework and generic feedback for the exam. |
| Exam Information |
| Exam Diet |
Paper Name |
Hours & Minutes |
|
| Main Exam Diet S2 (April/May) | | 3:00 | |
Learning Outcomes
On completion of this course, the student will be able to:
- Characterise an applied problem as a machine learning task and identify appropriate methods to address it
- Critically evaluate alternative machine learning approaches for application
- Originate new variants of machine learning approaches and demonstrate their applicability to problems
- Design implementation and refining programmes for learning algorithms in practice
- Demonstrate an ability to generate easy to understand descriptions of the nature of machine learning approaches in practice
|
Reading List
The below are indicative texts:
Machine Learning: A Probabilistic Perspective. Kevin P Murphy.
Bayesian Reasoning and Machine Learning. David Barber.
Pattern Recognition and Machine Learning, Christopher Bishop. |
Additional Information
| Graduate Attributes and Skills |
Not entered |
| Keywords | Not entered |
Contacts
| Course organiser | Dr Adam Ntakaris
Tel:
Email: |
Course secretary | Mrs Kelly-Ann De Wet
Tel: (0131 6)50 8071
Email: |
|
|
University Homepage