25883 AI-driven Compliance, Anomaly and Fraud Detection

Warning: The information on this page is indicative. The subject outline for a particular session, location and mode of offering is the authoritative source of all information about the subject for that offering. Required texts, recommended texts and references in particular are likely to change. Students will be provided with a subject outline once they enrol in the subject.

Subject handbook information prior to 2025 is available in the Archives.

UTS: Business: Finance
Credit points: 6 cp

Subject level:

Postgraduate

Result type: Grade and marks

Requisite(s): 24 credit points of completed study in spk(s): C04048 Master of Finance OR 24 credit points of completed study in spk(s): C04258 Master of Finance (Extension) OR 24 credit points of completed study in spk(s): C07021 Graduate Diploma Finance OR 24 credit points of completed study in 24Credit Points spk(s): MAJ08984 c 36cp Finance Major MBA
The lower case 'c' after the subject code indicates that the subject is a corequisite. See definitions for details.
These requisites may not apply to students in certain courses. See access conditions.

Description

In the fast-paced and complex world of finance, ensuring compliance and preventing fraud are paramount. This subject explores the role of artificial intelligence (AI) in mitigating these risks and safeguarding the integrity of financial systems. This subject introduces students to a captivating realm where AI technologies hold the key to uncovering hidden patterns, detecting irregularities, and fortifying compliance measures. Students gain a solid conceptual foundation in cutting-edge techniques, methodologies, and ethical considerations associated with leveraging AI for these vital tasks. Real-life scenarios are presented to illustrate the pressing need for advanced technologies in the finance industry.

Students are immersed in the world of data integration and processing, feature engineering, ensemble methods, and text mining techniques, witnessing how AI can consolidate diverse datasets and transform raw information into actionable insights. To help navigate the delicate balance between technological advancements and responsible AI usage, the subject delves into the ethical dimensions, examining the risks of algorithmic bias, data privacy concerns, and the need for transparency and accountability in implementing AI solutions. Upon completion, students emerge well-prepared to tackle the multifaceted challenges of the finance industry. They possess the knowledge and skills to effectively leverage AI technologies for detecting financial irregularities, making data-driven decisions, and ensuring the trust and confidence of investors and clients.

Subject learning objectives (SLOs)

1.	Examine AI technologies that address compliance challenges, detect anomalies, and prevent fraud in finance
2.	Evaluate and mitigate ethical risks associated with AI implementation in financial contexts
3.	Analyze and solve complex finance-related problems using AI-driven approaches
4.	Communicate AI-driven insights effectively to diverse stakeholders
5.	Critically reflect on rights to consent, privacy, and data sovereignty in AI applications for finance, especially regarding working ethically for or with Indigenous Australians

Course intended learning outcomes (CILOs)

This subject also contributes specifically to the following program learning objectives:

• Collaborate with colleagues, clients, and stakeholders from multidisciplinary backgrounds to develop and implement AI-based strategies, projects, and initiatives that achieve desired outcomes while considering business objectives, regulatory requirements, and ethical standards (2.2)
• Ensure ethical AI practices in finance that are inclusive, fair, and transparent (3.1)
• Critically reflect on the rights to consent, privacy, data sovereignty and self determination to work ethically with and for Indigenous Australians across finance professions (5.1)

Contribution to the development of graduate attributes

The subject contributes to the aim of preparing students for fulfilling and effective careers in business and finance by bridging the gap between AI and finance, addressing the industry's emerging needs and equipping students with the necessary knowledge, skills, and ethical considerations to excel in the evolving field of AI in finance. It contributes particularly to the development of the following graduate attributes:

• Intellectual rigour and innovative problem solving
• Communication and collaboration
• Social responsibility and cultural awareness
• Professional and technical competence

Teaching and learning strategies

Students will have pre-readings to complete before in class lectures/seminars and discussions, including a mix of chapters, journal articles, industry reports, and press. Additional (optional) extension materials will be provided in the form of recorded videos and further readings to allow students to delve deeper into topics of particular interest. Quizzes will be used for students to get feedback on their comprehension of the subject matter. Students will present their application proposals in class to obtain instant feedback and promote the exchange of ideas. Students will work in small groups on empirical exercises to encourage cohort building and peer learning.

Content (topics)

• Feature Engineering for Anomaly Detection
• Text Mining and NLP for Compliance
• Machine Learning for Fraud Detection
• Ethical Considerations, Transparency and Accountability in AI
• Regulatory Compliance and AI
• Future Trends and Challenges

Assessment

Assessment task 1: Empirical Assignment (Small group)

Objective(s):	This addresses subject learning objective(s): 3 and 4 This addresses program learning objectives(s): 2.2
Weight:	25%
Length:	Students will submit Python notebook (roughly 9 hours to construct)
Criteria:	Applicability of selected data to the project's objectives Appropriateness of methods used for estimating measures or engineering features Ability to draw meaningful conclusions Clear and concise expression of ideas and findings Balanced involvement of all team members

Assessment task 2: Case Study Assignment (Individual)

Objective(s):	This addresses subject learning objective(s): 1, 2 and 3
Weight:	30%
Length:	Students will submit a (maximum) 5,000-word report
Criteria:	Significance of the chosen case study to financial markets or services Detailed examination of the technological aspects involved Assessment of the technology's effect on financial markets or services Evaluation of how the technology addresses or creates risks and compliance, and ethical issues Clear articulation of ideas and findings

Assessment task 3: AI Application Proposal (Individual)

Intent:	Part A: AI application proposal (30%) Part B: Critical reflection (15%)
Objective(s):	This addresses subject learning objective(s): 3, 4 and 5 This addresses program learning objectives(s): 3.1 and 5.1
Weight:	45%
Length:	Students will submit a (maximum) 7,000-word report
Criteria:	Part A Feasibility of proposed AI solution Appropriate justification of choices Novelty of the AI-driven solution being proposed Appropriate mitigation measures for ethical risks associated with AI implementation Part B Depth of critical reflection on implications of data collection & AI use on working with and for Indigenous Australians

Minimum requirements

Students must achieve at least 50% of the subject’s total marks.

Required texts

• None