ICM317-Machine Learning and Big Data in Finance

Module Provider: ICMA Centre
Number of credits: 20 [10 ECTS credits]
Terms in which taught: Spring term module
Non-modular pre-requisites:
Modules excluded:
Current from: 2020/1

Module Convenor: Mr Mininder Sethi

Email: m.sethi@icmacentre.ac.uk

Type of module:

Summary module description:

In this module you will learn how machine learning techniques borrowed from artificial intelligence can be used to solve common big data problems in finance. We will first explore the issues related to the collection, organisation and visualisation of large sets of structured and unstructured data. With the use of Python we then explore ways in which a computer can be trained to recognise patterns in the data and its popular finance applications. For instance, we will look at stock price forecasting, company default prediction and market sentiment analysis.


The module focuses on (1) issues facing big data handling (2) high level description of distributed storage and processing of big data (Hadoop) (3) retrieval, organisation and cleaning of structured and unstructured data (4) visual analysis of a dataset (5) common machine learning techniques such as logistic regression, decision trees, K-nearest neighbours, k-means clustering, principal component analysis and deep learning tools like neural networks (6) finance applications.

Assessable learning outcomes:

By the end of the module it is expected that students will:

Understand how big data and artificial intelligence are changing our lives and creating business opportunities

Be familiar with the main issues in distributed storage and processing of big data

Understand the basic techniques for the collection and cleaning of large structured and unstructured data;

Understand the need for a rigorous data science approach and the concepts of training data, validation data and testing data;

Be able to build machine learning models and interpret the models in terms of their structure and accuracy;

Understand how big data and machine learning can be used to solve old and new problems in finance

Additional outcomes:

The module will use the industry standard Python programming language and will build on the programming skills developed in Part 1.

Outline content:

  1. Big data – a global multi-sector view

  2. Distributed storage and processing of big data (Hadoop)

  3. Structured and unstructured data collection, organisation, storage and cleaning

  4. Artificial intelligence, machine learning, deep learning

  5. Linear and logistic regression models in Python and finance applications

  6. Decision Tree Models in Python and finance applications

  7. K-nearest neighbours a nd k-means clustering in Python and finance applications

  8. Principal component analysis in Python and finance applications

  9. Deep learning and neural networks in Python and finance applications

  10. Big data and machine learning: case studies

Global context:

The module covers industry standard techniques using international datasets. The concepts are applied in investment banks, central banks, hedge funds and asset management firms worldwide.

Brief description of teaching and learning methods:

The core theory and concepts will be presented during lectures. Problem sets will be solved in workshops.

Contact hours:
  Autumn Spring Summer
Lectures 20
Seminars 10
Guided independent study:      
    Wider reading (independent) 50
    Wider reading (directed) 20
    Preparation for seminars 20
    Revision and preparation 30
    Essay preparation 30
    Reflection 20
Total hours by term 0 0
Total hours for module 200

Summative Assessment Methods:
Method Percentage
Report 40
Class test administered by School 60

Summative assessment- Examinations:

Summative assessment- Coursework and in-class tests:

Students will be asked to complete a report (40%) in week 2 of the summer term and two in class multiple choice tests (30% each) in weeks 7 and 11 of the spring term.

Formative assessment methods:

Seminar questions are assigned for each class. The seminar leader will facilitate discussion and offer feedback.

Penalties for late submission:

Penalties for late submission on this module are in accordance with the University policy. Please

refer to page 5 of the Postgraduate Guide to Assessment for further information:


Assessment requirements for a pass:

50% weighted average mark

Reassessment arrangements:

Re assessment of individual report

Additional Costs (specified where applicable):

Last updated: 4 April 2020


Things to do now