| Unit name | Quantitative Methods, Big Data and Machine Learning |
|---|---|
| Unit code | ACFIM0005 |
| Credit points | 20 |
| Level of study | M/7 |
| Teaching block(s) |
Teaching Block 1 (weeks 1 - 12) |
| Unit director | Dr. Tao |
| Open unit status | Not open |
| Units you must take before you take this one (pre-requisite units) |
None |
| Units you must take alongside this one (co-requisite units) |
AI, Blockchain Technology and Applications; Finance |
| Units you may not take alongside this one |
None |
| School/department | School of Accounting and Finance - Business School |
| Faculty | Faculty of Social Sciences and Law |
Why is this unit important?
By its nature, finance is a quantitative discipline, and in this unit, students will learn some of the techniques required to analyse financial data, understand the academic finance literature, and solve financial problems. The econometric models presented in this unit also underpin much of the work conducted by quantitative researchers and analysts in the financial markets, and thus they represent valuable industry knowledge. The emphasis throughout the unit is on applications rather than model derivations, and students will learn how to select and implement their own models using a software package.
The unit will also explain how machine learning (ML) is supporting organisations and individuals to make more effective investment decisions. It will present a range of applications of ML techniques to real-world problems in finance such as credit scoring, document sentiment assessment, return prediction, market and liquidity risk measurement, automated financial advice.
How does this unit fit within your programme of study?
This unit covers the core material on the analytical techniques of finance and financial technology that will be used in the Algorithmic Trading and Empirical Finance for Financial Technology units undertaken in teaching block 2. At this early stage in the programme, participants will learn vital industry skills in the handling and analysis of large and complex datasets. Students will be able to compare and contrast the more contemporary and sophisticated techniques that are the subject matter of ML with the more conventional classical statistical models used in econometrics, noting their relative strengths and weaknesses. Students will undertake empirical applications of machine learning techniques using a programming language, which they can draw on when conducting analysis as part of their dissertations. Examples and implementations of the methods covered in this unit will also be presented in several other units, including Finance and Algorithmic Trading. Quantitative Methods, Big Data and Machine Learning will lay the groundwork for the statistical aspects of these units and several of the optional units and many students will apply the techniques they learn on this unit in their Dissertation.
An overview of the content
This unit introduces the econometric techniques most commonly used in finance, including multiple regression methods and time-series analysis. Students will learn how to interpret fitted empirical models from statistical and financial perspectives. They will also develop the skills to execute their own econometric models to analyse specific datasets using a software package.
Students will learn machine learning techniques and appreciate how they are different to more conventional statistical models, being able to critically compare the two approaches. A wide range of ML techniques will be discussed, including: k-means clustering, nearest neighbour estimation, support vector machines, decision tree analysis, artificial neural networks, regularisation, feature selection methods, boosting and bagging, natural language processing, reinforcement learning, deep learning. The unit will also examine the methods available for ML model estimation, including numerical optimisation and maximum likelihood, and how data mining is applied to large datasets. Metrics for the interpretation and evaluation of the performance of fitted models will be presented and compared.
How will students, personally, be different as a result of the unit
Students will gain confidence in both analysing financial data using quantitative models and criticising the specifications estimated by academic researchers. They will also develop applied problem-solving skills, being able to select and implement the most appropriate tools to explore their data validly and address a particular problem.
Students will become confident in discussing how ML is used in financial applications, developing both a high-level understanding of the various methods and the ability to implement them in a programming language. They will develop industry skills in handling and analysis of both structured and unstructured data and will develop their analytical thinking and problem-solving abilities. They will learn to deal with complexity and handle situations where there are many possible approaches, and they will be able to interpret and critique the implementations of machine learning in academic studies.
Intended learning outcomes
Upon successful completion, students will be able to:
The core material will be covered in weekly two-hour lectures, which will cover a mixture of ‘theory’ and applications to relevant areas of finance. Students will also attend weekly computer lab sessions where they will learn how to implement the models presented in the lectures using a programming language (such as Python) with industry-relevant data and applications. The lab-sessions will be in small groups to facilitate interaction. The lecturer will provide optional advice and feedback sessions where students will be able to pose further questions regarding the material or ask about additional resources. A thematically organised discussion board will be set up on Blackboard and moderated by the lecturer to enable student-directed discussion of topic areas where they have particular concerns. A weekly resource list will be provided via Blackboard and Talis Aspire comprising recommended readings and YouTube videos for self-study. Guidance will be given for working in groups and preparing joint reports through a tutorial and support will continue throughout the period while the group assignment is live.
Tasks which will help you learn and prepare forsummative tasks (formative)
Students will participate in weekly tutorials where non-assessed problem sets that they have prepared in advance will be discussed and generic oral feedback will be offered. Regular on-line multiple-choice quizzes will be used for students to assess their own understanding and to identify areas of the syllabus requiring additional study. There will also be weekly computer lab classes where students will work individually and in small groups to implement econometric or machine learning problems and they will be provided with oral feedback on their proposed solutions. Written feedback on non-assessed problem sets will be available through Blackboard after the classes have taken place. Multiple-choice (formative) tests will also be made available on Blackboard for students to complete and test their understanding of the material where feedback will be provided automatically. A sample exam paper with worked answers will be provided on Blackboard and a revision lecture will be organised at the end of the teaching block to prepare students for the final examination. Support for working in groups and completing the groupwork will be provided.
Tasks which count towards your unit mark (summative)
When assessment does not go to plan
Students who fail the unit overall at the first attempt will be expected to resit all the assessments that they were unsuccessful in. Students failing the group project will undertake an individual project for the reassessment. The resit exam will have an identical structure to that of the first sit exam.
If this unit has a Resource List, you will normally find a link to it in the Blackboard area for the unit. Sometimes there will be a separate link for each weekly topic.
If you are unable to access a list through Blackboard, you can also find it via the Resource Lists homepage. Search for the list by the unit name or code (e.g. ACFIM0005).
How much time the unit requires
Each credit equates to 10 hours of total student input. For example a 20 credit unit will take you 200 hours
of study to complete. Your total learning time is made up of contact time, directed learning tasks,
independent learning and assessment activity.
See the University Workload statement relating to this unit for more information.
Assessment
The Board of Examiners will consider all cases where students have failed or not completed the assessments required for credit.
The Board considers each student's outcomes across all the units which contribute to each year's programme of study. For appropriate assessments, if you have self-certificated your absence, you will normally be required to complete it the next time it runs (for assessments at the end of TB1 and TB2 this is usually in the next re-assessment period).
The Board of Examiners will take into account any exceptional circumstances and operates
within the Regulations and Code of Practice for Taught Programmes.
