Course Outline
Module 1 – Introduction to Generative AI in Financial Context
• Overview of Generative AI and Large Language Models
• Evolution from traditional AI/ML to GenAI in finance
• Key use cases in financial services: risk analytics, investment research, compliance, and
client reporting
• Opportunities and challenges in adopting GenAI in regulated environments
Hands-on Exercise:
Exploring GenAI tools (ChatGPT, Claude, Gemini) for finance-related queries
Module 2 – Inside the Black Box: Understanding LLMs
• How LLMs are built and trained (architecture, parameters, data sources)
• Tokenization, embeddings, and contextual understanding
• Why hallucinations occur — cognitive analogy and technical roots
• Fine-tuning and retrieval-augmented generation (RAG) for financial data
• Evaluating model reliability and accuracy
Practical Demo:
Testing model outputs and diagnosing hallucinations
Module 3 – Prompt Engineering for Quantitative Analysts
• Principles of effective prompting
• Prompt structures for analytical tasks (e.g., data interpretation, risk scenario generation)
• Building multi-step prompts for financial forecasting
• Chain-of-thought prompting and verification techniques
• Using system and role prompts to guide GenAI responses
Hands-on Workshop:
Create prompts to generate and validate investment risk analysis reports
Module 4 – Applying GenAI to Financial Risk Management
• Integrating GenAI with traditional ML models in risk workflows
• Automating credit and market risk assessments with LLMs
• Using GenAI for stress testing, model documentation, and audit trails
• Incorporating alternative data (news, reports, ESG metrics) using GenAI
• Managing data privacy, confidentiality, and compliance with AI governance
Practical Exercise:
Simulate a financial risk management scenario using GenAI-assisted tools
Module 5 – Hallucination, Reliability, and AI Risk Controls
• Recognizing and addressing hallucination and overconfidence in outputs
• Validation frameworks for GenAI-generated financial content
• Transparency, explainability, and reproducibility in LLM use
• Designing internal control policies for AI-assisted decision-making
Case Study:
Examples of AI errors in finance and mitigation strategies
Module 6 – Strategic Integration and Media Planning for AI in Finance
• Developing a GenAI adoption roadmap for financial institutions
• Aligning GenAI projects with organizational risk appetite
• Building a cross-functional governance model for AI initiatives
• KPIs and ROI tracking for GenAI in financial analytics
Group Activity:
Design an internal AI usage policy for the risk management department
Requirements
Testimonials (4)
Understanding of AI and LLM. How it works and ehat the watchouts and opportunities are!
Henk Jan Beltman - genuine business
Course - Advanced AI Concepts with Perplexity
Comprehensiveness about the backround; how to do a prompt.
Olaf Kannt - Helios Klinikum Krefeld
Course - Generative AI and Prompt Engineering in Healthcare
the tips and recommended prompts that we can take away from this training
Lee Mei Lin - ST Engineering IHQ Pte Ltd
Course - InVideo AI: Creating Engaging Short-Form Videos
use of proper and effective prompt