This course provides a comprehensive introduction to machine learning (ML) techniques in finance, focusing on their theoretical foundations and practical applications in financial data analysis. Students will explore key ML methods-such as classifiers, neural networks, and Gaussian process regression-and their roles in extending traditional financial models. With hands-on training in Python and industry-standard libraries, students will build technical proficiency in implementing and interpreting ML models for high-dimensional financial datasets.

In addition to technical skills, the course emphasizes ethical considerations, exploring responsible data use and bias mitigation in ML-driven financial models. Collaborative and experiential learning activities simulate real-world financial challenges, enhancing teamwork and critical thinking skills. By integrating global perspectives and sustainability into financial analysis, students are prepared to tackle complex, data-driven challenges in modern finance, making them well-equipped for careers in quantitative finance, asset management, and financial technology.

10 x 2 hours mix of lectures and workshops
6 x 1.5 hours computer labs

None

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.

Normally, the group-based assessment listed above cannot be reassessed.

This course aims to equip students with a comprehensive understanding of machine learning (ML) techniques as applied to economic and financial data analysis, emphasizing the unique challenges and nuances of working with financial datasets. Specifically, the course aims to:

■ Develop students' ability to apply a structured data mining approach-covering objective specification, data curation and exploration, data cleaning, feature selection, model selection, parameter tuning, and evaluation-to analyze complex financial data.

■ Foster critical skills in selecting appropriate ML algorithms and optimization techniques based on the characteristics of a given financial dataset and problem domain.

■ Provide hands-on experience in Python, with a focus on standard ML libraries and packages, enabling students to programmatically analyze large volumes of financial data and derive meaningful insights.

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

1. Formulate the objectives of machine learning (ML) problems in finance and implement effective solutions using Python and standard ML libraries.

2. Select and apply appropriate optimization algorithms and methods tailored to specific ML applications in finance.

3. Critically evaluate financial datasets, considering the computational requirements and performance constraints of various ML algorithms.

4. Design and develop ML applications collaboratively, working effectively in small groups to solve complex financial problems programmatically.

Students must submit at least 75% by weight of the components (including examinations) of the course's summative assessment.