Overview

Topics may include:

Machine learning in the business and finance context; Artificial neural networks, Support vector machines and their applications in business and finance; Deep learning; Tensor flow and Keras; Natural language processing (NLP): theory, applications and limitations; Ongoing and future research in NLP in business and finance; Deep learning applied to text and sequences; Data science, machine learning and business strategy.

Assessment Strategy

Two reports based on different elements of the module content and learning outcomes.

Excellent: A- to A+ (70%+): Outstanding performance. The relevant information accurately deployed. Excellent grasp of theoretical/conceptual/practice elements. Good integration of theory/practice/information in pursuit of the assessed work's objectives. Strong evidence of the use of creative and reflective skills.

Good: B- to B+ (60-69%): Very good performance. Most of the relevant information accurately deployed. Good grasp of theoretical/conceptual/practical elements. Good integration of theory/practice/information in pursuit of the assessed work's objectives. Evidence of the use of creative and reflective skills. of the use of creative and reflective skills.

Satisfactory: C- to C+ (50-59%): Much of the relevant information and skills mostly accurately deployed. Adequate grasp of theoretical/conceptual/practical elements. Fair integration of theory/practice/information in the pursuit of the assessed work's objectives. Some evidence of the use of creative and reflective skills.

Threshold: D- to D+ (40-49%): No major omissions or inaccuracies in the deployment of information/skills. Some grasp of theoretical/conceptual/practical elements. Integration of theory/practice/information present intermittently in pursuit of the assessed work's objectives.

Learning Outcomes

• Apply statistical techniques and mathematical reasoning to formulate machine learning tools for data analysis in business and finance.

• Apply the communication framework for translating data analysis into decision making outcomes.

• Apply the language, thinking and tools of data retrieval and manipulation to business and finance problems.

• Articulate and analyse the inputs, outputs, relationships, boundaries, and data transformations of digital systems in business and finance.

• Design, train and utilise neural networks, support vector machines and ensemble tree models for business data systems.