THE UNIVERSITY of EDINBURGH

DEGREE REGULATIONS & PROGRAMMES OF STUDY 2024/2025

Timetable information in the Course Catalogue may be subject to change.

University Homepage
DRPS Homepage
DRPS Search
DRPS Contact
DRPS : Course Catalogue : Business School : Common Courses (Management School)

Postgraduate Course: Large Language Models in Business Analytics (CMSE11654)

Course Outline
SchoolBusiness School CollegeCollege of Arts, Humanities and Social Sciences
Credit level (Normal year taken)SCQF Level 11 (Postgraduate) AvailabilityNot available to visiting students
SCQF Credits10 ECTS Credits5
SummaryThis course equips students with a deep understanding of how Large Language Models (LLMs) can assist data analytics and decision-making processes in various sectors. It emphasises the development of critical thinking skills necessary to analyse and evaluate the implications of LLMs in various contexts. Students will explore the fundamental concepts behind LLMs, their development, deployment, and the ethical considerations surrounding their use. This approach ensures that graduates can apply these models to solve complex business problems while engaging in informed discussions and forming well-reasoned opinions about the development and deployment of these technologies.

The course integrates the discussion of ethical and societal impacts of AI technologies, preparing students to become responsible leaders in the field. By fostering critical thinking skills, students will be able to assess the potential benefits and challenges associated with LLMs, and make informed decisions regarding their implementation in real-world scenarios. Through case studies and discussions, students will develop the ability to think critically about the role of LLMs in shaping the future of various industries and society as a whole.
Course description This course offers an explorative study of Large Language Models (LLMs), starting from the basics of AI and machine learning to the intricate architectures and concepts underpinning LLMs, with a focus on Transformer models and NLP(Natural Language Processing). It advances into prompt engineering techniques that aims to enhancing LLM's problem-solving abilities. The curriculum also explores LLM's diverse applications in various sectors, emphasising their potential to improve efficiency and augment human tasks. The course concludes with real-world case studies and a discussion on the ethical implications of LLM use, addressing biases, privacy, and ethical AI deployment strategies, providing a holistic view of LLM's capabilities and challenges in modern applications.

Outline content

Week 1: Foundations of Large Language Models

- Introduction to artificial intelligence and machine learning principles.

- Comprehensive overview of Large Language Models (LLMs): architecture, key developments, and fundamental concepts, focusing on Transformer models and natural language processing (NLP).


Week 2: Prompt Engineering

- Deep dive into prompt engineering: basic principles for crafting effective prompts to elicit desired responses from LLMs.

- Exploring different prompt strategies, such as CoT(Chain-of-Thought) and ToT(Tree-of-Thought), to enhance problem-solving and reasoning capabilities.


Week 3: Integration with Business Analytics Workflows

- Examination of LLMs' wide-ranging applications across various sectors, including anomaly detection, classification and data interpretation, in particular focusing on the capability of transforming unstructured data.

- Insight into LLMs' potential to streamline processes and boost operational efficiency.

- Workshop: Prompt Engineering


Week 4: Techniques for LLM Customisation

- Detailed explanation of methods for tailoring LLM outputs, including prompt tuning and fine-tuning.

- Introduction of LLM evaluation techniques.

- Workshop: LLM application


Week 5: Real-World Case Studies and Ethical Considerations

- Analysis of projects that demonstrating the development and deployment of LLM-based solutions to address complex business challenges.

- Discussion on the ethical implications of LLM applications, focusing on potential biases, privacy issues, and copyright infringement.
Entry Requirements (not applicable to Visiting Students)
Pre-requisites Co-requisites
Prohibited Combinations Other requirements None
Course Delivery Information
Academic year 2024/25, Not available to visiting students (SS1) Quota:  None
Course Start Block 3 (Sem 2)
Timetable Timetable
Learning and Teaching activities (Further Info) Total Hours: 100 ( Lecture Hours 10, Seminar/Tutorial Hours 2, Programme Level Learning and Teaching Hours 2, Directed Learning and Independent Learning Hours 86 )
Assessment (Further Info) Written Exam 0 %, Coursework 30 %, Practical Exam 70 %
Additional Information (Assessment) 70% Presentation (Group) - Assesses all course Learning Outcomes
30% Project report (Indivdiual) - Assesses all course Learning Outcomes
Feedback Formative: Feedback will be provided throughout the course.

Summative: Feedback will be provided on assessments within agreed deadlines.
No Exam Information
Learning Outcomes
On completion of this course, the student will be able to:
  1. Grasp the foundational principles of artificial intelligence and machine learning, with a deep understanding of Large Language Models (LLMs), including their architecture and evolution.
  2. Employ prompt engineering and advanced thought models like Chain of Thoughts and Tree of Thoughts to enhance LLMs' problem-solving and reasoning capabilities.
  3. Identify and apply LLMs across diverse fields such as classification and anomaly detection, recognising their role in augmenting human tasks and improving efficiency.
  4. Master prompt tuning and fine-tuning techniques to customise LLM outputs for specific applications, evaluating the effectiveness of these methodologies in various scenarios.
  5. Analyse real-world case studies to understand the development and application of LLM-based solutions, alongside an awareness of the ethical considerations surrounding the use of LLMs in technology.
Reading List
Core text

Prompt Engineering for Generative AI by James Phoenix, Mike Taylor. Publisher(s): O'Reilly Media, Inc.
Additional Information
Graduate Attributes and Skills Practice: Applied Knowledge, Skills and Understanding

After completing this course, students should be able to:

Apply creative, innovative, entrepreneurial, sustainable and responsible business solutions to address social, economic and environmental global challenges.

Work with a variety of organisations, their stakeholders, and the communities they serve - learning from them, and aiding them to achieve responsible, sustainable and enterprising solutions to complex problems.

Communication, ICT, and Numeracy Skills

After completing this course, students should be able to:

Critically evaluate and present digital and other sources, research methods, data and information; discern their limitations, accuracy, validity, reliability and suitability; and apply responsibly in a wide variety of organisational contexts.

Cognitive Skills

After completing this course, students should be able to:

Be self-motivated; curious; show initiative; set, achieve and surpass goals; as well as demonstrating adaptability, capable of handling complexity and ambiguity, with a willingness to learn; as well as being able to demonstrate the use digital and other tools to carry out tasks effectively, productively, and with attention to quality.

Knowledge and Understanding

After completing this course, students should be able to:

Demonstrate a thorough knowledge and understanding of contemporary organisational disciplines; comprehend the role of business within the contemporary world; and critically evaluate and synthesise primary and secondary research and sources of evidence in order to make, and present, well informed and transparent organisation-related decisions, which have a positive global impact.

Identify, define and analyse theoretical and applied business and management problems, and develop approaches, informed by an understanding of appropriate quantitative and/or qualitative techniques, to explore and solve them responsibly.
KeywordsLarge Language Models,Predictive Analysis,Digital Technology
Contacts
Course organiserDr Tong Wang
Tel: (0131 6)51 5551
Email: Tong.Wang@ed.ac.uk
Course secretaryMiss Quinny Jiang
Tel:
Email: Quinny.Jiang@ed.ac.uk
Navigation
Help & Information
Home
Introduction
Glossary
Search DPTs and Courses
Regulations
Regulations
Degree Programmes
Introduction
Browse DPTs
Courses
Introduction
Humanities and Social Science
Science and Engineering
Medicine and Veterinary Medicine
Other Information
Combined Course Timetable
Prospectuses
Important Information