Last modified: 23 Jul 2024 10:43
This course will introduce machine learning, artificial intelligence and forecasting with applications in finance. The course will explore recent trends in FinTech, which are based on data analytics and recent advances in machine learning.
The course is based on Python, which has become the dominant general-purpose programming language in data analytics and machine learning.
Students are required to take CS5076 Introduction to Programming in the first sub-session; hence, the course expects a basic level of programming skills in Python.
| Study Type | Postgraduate | Level | 5 |
|---|---|---|---|
| Term | Second Term | Credit Points | 15 credits (7.5 ECTS credits) |
| Campus | Aberdeen | Sustained Study | No |
| Co-ordinators |
|
||
The course is structured into ten units and associated tutorials.
Unit 1: Introduction
Big data, machine learning, artificial intelligence (AI) and its applications in finance and management.
Unit 2: A Python bootcamp
This unit refreshes some key principles in Python including algorithmic thinking, objects, lists, tuples and arrays, strings, loops, while / if, array operations, branching, nesting, data import, visualisation of data.
Unit 3: APIs and web-scraping
Getting access to online data, APIs to access Yahoo Finance and other sources, access to intra-daily data, implementation in Python
Unit 4: What is machine learning?
Types of machine learning, artificial neurons, perception learning algorithm
Unit 5: Machine learning classifiers
Introduction to scikit-learn, logistic regression, maximum margin, non-linear problems
Unit 6: Dimensionality reduction
Principal component analysis (PCA), supervised and unsupervised learning, nonlinear mappings
Unit 7: Artificial Intelligence
Definitions of AI, building a neural network in Python
Unit 8: Fintech
Big data in finance, peer-to-peer lending, online / mobile banking, cryptos
Unit 9: Forecasting
In-sample versus out-of-sample forecasting, comparison of forecasting tools
Unit 10: Fully automated trading system
Develop a trading bot, testing and implementation of trading strategies
Information on contact teaching time is available from the course guide.
| Assessment Type | Summative | Weighting | 75 | |
|---|---|---|---|---|
| Assessment Weeks | Feedback Weeks | |||
| Feedback |
Written feedback will be provided outlining whether and how students met the learning outcomes. |
|||
| Knowledge Level | Thinking Skill | Outcome |
|---|---|---|
| Conceptual | Understand | Understand the role of big data and its applications in finance and management. |
| Procedural | Evaluate | By the end of this course students shall critically evaluate the processes and practices of machine learning and artificial intelligence |
| Reflection | Create | Develop programming skills in Python to analyse data and create machine learning code. |
| Assessment Type | Summative | Weighting | 25 | |
|---|---|---|---|---|
| Assessment Weeks | Feedback Weeks | |||
| Feedback |
Includes a Report |
|||
| Knowledge Level | Thinking Skill | Outcome |
|---|---|---|
|
|
||
There are no assessments for this course.
| Assessment Type | Summative | Weighting | 100 | |
|---|---|---|---|---|
| Assessment Weeks | Feedback Weeks | |||
| Feedback |
Written feedback will be provided outlining wether and how students met the learning outcomes. |
Word Count | 2000 | |
| Knowledge Level | Thinking Skill | Outcome |
|---|---|---|
|
|
||
| Knowledge Level | Thinking Skill | Outcome |
|---|---|---|
| Reflection | Create | Develop programming skills in Python to analyse data and create machine learning code. |
| Conceptual | Understand | Understand the role of big data and its applications in finance and management. |
| Procedural | Evaluate | By the end of this course students shall critically evaluate the processes and practices of machine learning and artificial intelligence |
We have detected that you are have compatibility mode enabled or are using an old version of Internet Explorer. You either need to switch off compatibility mode for this site or upgrade your browser.
