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

1. Written assignment, including essay; Individual; 2650 words; 75%; ILOs 1-3.
2. Written assignment, including essay; Group; 2250 words; 25%; ILOs 1-4.

It is the default expectation that all courses will offer opportunities for reassessment or deferred assessment. Where it is not possible to offer this in some assessment components, the grade achieved at the first attempt will be counted towards the final course grade, and any exceptions for this course are described below.

[No exceptions]

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.