DCU Home | Our Courses | Loop | Registry | Library | Search DCU

Module Specifications..

Current Academic Year 2023 - 2024

Please note that this information is subject to change.

Module Title Financial Machine Learning and Automation
Module Code EF5178
School DCUBS
Module Co-ordinatorSemester 1: Michael Dowling
Semester 2: Michael Dowling
Autumn: Michael Dowling
Module TeacherNo Teacher Assigned
NFQ level 9 Credit Rating 7.5
Pre-requisite None
Co-requisite None
Compatibles None
Incompatibles None
Coursework Only

This module develops knowledge of the techniques of machine learning to learn from financial data and build new types of financial models. Through the application of artificial neural networks, support vector machines, random forests, and gradient boosting, we will bring new understanding to financial models. The machine learning techniques are applied to build, for example, asset pricing models, credit acceptance / rejection models, and fraud detection models. There will also be coverage of the practical issues of setting up secure data infrastructures for implementing these techniques in the firm. A second focus will be on how to use machine learning, as well as other tools, to implement automation to financial services provision in the firm. The micro is delivered through the Python language.

Learning Outcomes

1. Demonstrate understanding of the key machine learning techniques of benefit to financial modeling
2. Apply machine learning techniques appropriately in a variety of practical financial context
3. Understand the data needs, and appropriate and secure data handling skills, for working with financial models
4. Implement automation to financial decision making based on financial machine learning and understanding of financial technology

Workload Full-time hours per semester
Type Hours Description
Lecture12Formal classes (lecture / workshop), one hour per week delivered live online, with a recorded option available.
Lecture12Formal classes (lecture), one hour per week delivered in pre-recorded online learning
Assignment Completion76Individual assignment and group project.
Independent Study87.5Class related reading and activities, guided reading and further learning.
Total Workload: 187.5

All module information is indicative and subject to change. For further information,students are advised to refer to the University's Marks and Standards and Programme Specific Regulations at: http://www.dcu.ie/registry/examinations/index.shtml

Indicative Content and Learning Activities

Regression-based machine learning
Exploration of various techniques associated with regression. Including setting up data for testing, pre-processing. To cover techniques such as linear regression, gradient boosting, random forests, MLP. Techniques to be applied through sklearn in Python with finance case studies.

Grouping-based machine learning
Exploration of various techniques associated with clustering and grouping. Starting with logistic regression, decision trees, SVM, deep learning clustering and grouping.

Other machine learning
Examining techniques such as outlier detection and its benefit for fraud detection and credit default risk in finance. Also examining (very briefly) the use of text-based machine learning models. Data security and data protection.

Automation for FinTech
Techniques and tools for implementing automation in financial technology. Examined from a robotic process automation perspective as well as a user experience perspective. Advice from expert practitioners on practical implementation.

Assessment Breakdown
Continuous Assessment0% Examination Weight100%
Course Work Breakdown
TypeDescription% of totalAssessment Date
Report(s)Individual assessment: The student will demonstrate learning through worksheet-based application of financial machine learning concepts. [Submitted around Week 9 of the module]50%Week 27
Group project Group work: Students will develop a financial project that incorporates machine learning to develop a financial model, and automation to allow some element of automated model decision making. There will be an individual reflective report attached to the group project (20%), as well as a group presentation (30%). [Submitted in end-of-teaching week]50%Sem 2 End
Reassessment Requirement Type
Resit arrangements are explained by the following categories;
1 = A resit is available for all components of the module
2 = No resit is available for 100% continuous assessment module
3 = No resit is available for the continuous assessment component
This module is category 1
Indicative Reading List

  • Aurélien Géron: 2019, Hands-on Machine Learning with Scikit-Learn, Keras, and TensorFlow, O'Reilly, 1492032646
  • Chris Albon: 2018, Python Machine Learning Cookbook, O'Reilly Media, 9781491989388
Other Resources

61307, 0, DataCamp (various courses), www.datacamp.com,
Programme or List of Programmes
MCMBSMicro-credential Modules DCUBS

My DCU | Loop | Disclaimer | Privacy Statement