Timetable information in the Course Catalogue may be subject to change.

University Homepage
DRPS Homepage
DRPS Search
DRPS Contact
DRPS : Course Catalogue : Business School : Common Courses (Management School)

Postgraduate Course: Pattern Recognition in Financial Data (CMSE11527)

Course Outline
SchoolBusiness School CollegeCollege of Arts, Humanities and Social Sciences
Credit level (Normal year taken)SCQF Level 11 (Postgraduate) AvailabilityAvailable to all students
SCQF Credits20 ECTS Credits10
SummaryThe study of Artificial Intelligence and the development of tools aimed at analysing data (e.g., high-frequency trading 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 that builds on the introduction to machine learning INFR11205 offers to help students develop further skills in the intelligent utilisation of machine learning methods in the context of financial data, such as high-frequency trading (HFT) and limit order book datasets (LOB). A key offering of this course is that students will gain access to real HFT LOB datasets and develop 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 IAML (INFR11205) focuses 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 such as HFT LOB datasets. 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. Furthermore, in order to maintain complementarity with other related courses on the MSc FTP, the course will also respond to changes in the curriculum of Financial Machine Learning (CMSE11475) and Financial Machine Learning II (Practical). However, the main topic headings are expected to be reasonably stable.

Outline Content

- 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 real forecasting problems such as stock price forecasting based on HFT frameworks

- 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
High Demand Course? Yes
Course Delivery Information
Academic year 2023/24, 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% Written exam (individual) - Assesses course Learning Outcomes 1, 2, 5
Feedback Formative: Feedback will be provided throughout the course.

Summative: Feedback will be provided on the assessments within agreed deadlines.
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:
  1. Characterise an applied problem as a machine learning task and identify appropriate methods to address it
  2. Critically evaluate alternative machine learning approaches for application
  3. Originate new variants of machine learning approaches and demonstrate their applicability to problems
  4. Design implementation and refining programmes for learning algorithms in practice
  5. Demonstrate an ability to generate easy to understand descriptions of the nature of machine learning approaches in practice
Reading List
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
KeywordsNot entered
Course organiserDr Adam Ntakaris
Course secretaryMiss Tamara Turford
Tel: (0131 6)50 8074
Help & Information
Search DPTs and Courses
Degree Programmes
Browse DPTs
Humanities and Social Science
Science and Engineering
Medicine and Veterinary Medicine
Other Information
Combined Course Timetable
Important Information