Course Catalogue

View Specification Document | Reading List

This course examines how the combination of data science and statistical learning techniques enable practitioners to translate information embedded in large-dimensional datasets to more efficient financial decisions. The course content comprehensively covers frontier theories, empirical methods, computational implementations, and applications used to formulate and address real-world financial problems. 

10 two-hour interactive lectures, 5 one-hour tutorials.

Prior familiarity with basic calculus and statistics would be helpful but not required. Please refer to the current postgraduate prospectus at: http://www.gla.ac.uk/postgraduate/

None

None

1. Quiz (10%)  The quiz will be accessible to start within a 24 hours window, and once started the allowed time to complete is 60 minutes. This is an individual assessment and only one attempt is allowed. The quiz comprises 10 multiple-choice questions covering course contents during the first four weeks including methodological learning outcomes, key facts and statistics arising from the numerical and empirical exercises.

2. Individual Assignment (30%) includes a problem sheet requiring methodological derivations, numerical computations followed by interpretation of results.

3. Group Assignment (20%) is based on class activities demonstrated during lecture sessions. Class participants are assigned to four groups. At each session one group -henceforth, the session's reporting group (RG)- is tasked to write a report on the class activity describing the main purpose, key takeaways and important remarks (1-2 pages). All other groups in that session-henceforth, the session's examining groups (EG's)- will be tasked to review the submission made by the RG. More specifically, EG's will serve as the peer-reviewers based on their own learning from the activity, thus it is essential that EG's, invest sufficient time and additional attention into the activity to develop a benchmark as the basis to evaluate RG's submission. All EG's are required to write their commentaries reviewing the RG's report and highlight areas of strengths and shortcomings in detail (1-1.5 pages). Each of the four class groups will serve once as a reporting group and separately three times as an examining group. All three peer-written commentaries provided by the EG's are marked by the course convenor as a formal assessment component counting towards 20% of the course grade.

4. Degree exam in April/May (40%): The final exam will be an individual assessment covering all course contents during the semester including key facts and statistics arising from empirical exercises, class reports and commentaries, methodological derivations and computations. Information regarding the final examination will be released towards the end of the semester.

Reassessments are normally available for all courses, except those which contribute to the Honours classification. Where, exceptionally, reassessment on Honours courses is required to satisfy professional/accreditation requirements, only the overall course grade achieved at the first attempt will contribute to the Honours classification. For non-Honours courses, students are offered reassessment in all or any of the components of assessment if the satisfactory (threshold) grade for the overall course is not achieved at the first attempt. This is normally grade D3 for undergraduate students and grade C3 for postgraduate students. Exceptionally it may not be possible to offer reassessment of some coursework items, in which case the mark achieved at the first attempt will be counted towards the final course grade. Any such exceptions for this course are described below. 

The course aims to

■ Develop a thorough understanding of financial and economic data classes, implementing dynamic data acquisition routines, pre-processing information, context-dependent anomaly detection procedures and structuring heterogenous data for the purpose of financial analysis. 

■ Provide a critical examination of linear, constrained linear and nonlinear estimation methods aimed for analysing large-dimensional datasets, including reduction and regularisation methods, variable selection and cross-validation techniques.

■ Provide an in-depth examination of supervised statistical learning and data-driven decision-making methods intended for formulating and addressing financial problems.

By the end of this course students will be able to:

1. Formulate real-world financial problems into statistical frameworks.

2. Implement data analytic software routines to acquire, structure and examine heterogenous financial datasets.

3. Critically examine reduction and regularisation methods to summarise large-dimensional datasets based on linear, constrained linear and nonlinear estimation methods.

4. Evaluate model performance and critically assess cross-model validation.

5. Develop data-driven decision-making routines with applications to risk management and asset allocation.

None