Data Science and Machine Learning in Finance ACCFIN5246
- Academic Session: 2023-24
- School: Adam Smith Business School
- Credits: 20
- Level: Level 5 (SCQF level 11)
- Typically Offered: Semester 2
- Available to Visiting Students: No
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.
Requirements of Entry
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/
1. Quiz (15%) - This is an individual assessment including multiple-choice questions and covering course contents during the first four weeks including methodological learning outcomes, key facts and statistics and empirical exercises.
2. Individual Assignment 1 (35%) - This is an individual assessment including a problem sheet requiring methodological derivations, and numerical computations followed by interpretation of results.
3. Individual Assignment 2 (50%) - This is an individual assessment including a problem sheet requiring methodological derivations, and numerical computations followed by interpretation of results based on the course contents throughout the entire semester.
1 hour, multiple-choice questions
Individual Assignment 1
Individual Assignment 2
The quiz and individual assignment 1 are intended to evaluate course learning outcomes in addition to providing a basis towards preparation for the individual assignments. All assignments share an overall common context and level to evaluate the course learning outcomes.
Main Assessment In: April/May
Are reassessment opportunities available for all summative assessments? No
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 heterogeneous data for the purpose of financial analysis.
■ Provide a critical examination of linear, constrained linear and nonlinear estimation methods aimed at 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.
Intended Learning Outcomes of Course
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 heterogeneous 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.
Minimum Requirement for Award of Credits