Module FINN3071: Quantitative Finance with Artificial Intelligence

Department: Finance

FINN3071: Quantitative Finance with Artificial Intelligence

Prerequisites

• Corporate Finance (FINN2041) AND Financial Econometrics 1 (FINN2031)

Corequisites

• Security Investment Analysis (FINN3021)

Excluded Combination of Modules

• None

Aims

• To provide students with knowledge and understanding of questions in quantitative finance linked to appropriate methodologies for their analysis.
• To enable students to rigorously explore issues in finance by using computer programming and professional data sources.
• To become familiar with the techniques for analysis employed in the quantitative finance industry and to evaluate the trading strategies used by market professionals.
• To develop applied machine learning (ML) competence for financial modelling and quantitative trading, including robust validation, interpretability and the critical assessment of when Machine Learning adds value over classical approaches.
• To provide students with the opportunity to develop the ability to critically evaluate academic literature relating to quantitative and computational finance.
• To offer the opportunity to develop key skills.

Content

• Introduction to quantitative and computational finance
• Using Python (and/or similar, e.g. 'R') with applications in finance: Syntax, data types and writing simple programs; Importing data and working with financial time series (including securities, foreign exchange and commodities); Plotting and visualisation of data; Loops and functions.
• The nature of quantitative trading strategies.
• Implementing quantitative trading strategies, including: stochastic asset pricing models; statistical arbitrage; deterministic models.
• Evaluating and analysing performance of trading strategies.
• ML framing for finance problems: prediction vs classification vs risk/regime tasks.
• Interpreting ML results and linking back to finance theory.
• Using agentic Artificial Intelligence tools as coding assistants for scoping, debugging, and refactoring, with required documentation and attribution.

Learning Outcomes

• On completion of this module students should have:
• developed an advanced knowledge of the central issues in quantitative finance;
• understanding of a programming language and its use to rigorously explore quantitative finance;
• understanding of core applied machine learning concepts relevant to financial data and quantitative research.

• On completion of this module students should have:
• academic skill to analyse the role of computational analysis in financial markets;
• the ability to evaluate the usage of computational and quantitative techniques by market professionals;
• written programs to critically analyse trading strategies employed by market participants, considering factors such as risk and slippage;
• become skilled at advanced usage of professional finance data sources and how to link these to appropriate software for analysis.
• developed skills in applying machine learning techniques to financial data and in critically evaluating their role in quantitative trading strategies.
• the ability to use AI-based coding assistants to support quantitative programming, with appropriate documentation and critical evaluation of their outputs.

• In addition, students will have had the opportunity to further develop the following key skills:
• written communication - through the formative and summative assignments;
• planning and organising - observing the strict assignment deadlines;
• problem solving - by applying appropriate analytical and quantitative skills to evaluate theoretical concepts using real data;
• initiative - by searching relevant literature, identifying recent developments in software packages and information in preparation of the summative assignment;
• numeracy - by analysing financial data;
• computer literacy - by writing complex programs to analyse financial data and evaluate trading systems. In addition, word-processing the assignments; downloading assignment information and notes from Blackboard.

Modes of Teaching, Learning and Assessment and how these contribute to the learning outcomes of the module

• Learning outcomes are met through weekly 3 hour in-person classroom-based workshops, supported by weekly 1 hour asynchronous online lectures which take the form of preparatory online resources.
• The workshops consist of a combination of taught input, computer practical sessions, group work, case studies and discussion.
• The weekly online resources provide preparatory material for the workshops typically consisting of directed reading and video content. Engagement with the weekly online resources by students in advance of the workshops is mandatory and essential to be able to participate in the workshops.
• Formative assessment is by means of an assignment. Feedback will be provided to each individual student which can then be built upon and developed for the summative coursework assignment. Written feedback and general suggestions will be communicated directly to students.
• Summative assessment is by means of an assignment designed around the development of programs and methodologies to analyse empirical problems and trading strategy issues, using data unique to each student.

Teaching Methods and Learning Hours

Summative Assessment

Formative Assessment:

One 1500 word assignment. This will be centred around problem solving using appropriate software.

■ Students who do not attend monitored activities shown under Teaching Methods and Learning Hours, or who fail to complete the summative or formative assessment(s) specified above, may be subject to the Academic Progress procedures defined in the University's General Regulation V, and may be required to leave the University.