Recommended Prerequisites:
- Basic Knowledge of Financial Markets: Understanding of stock markets, trading, and financial instruments.
- Familiarity with Machine Learning: Basic concepts and algorithms of machine learning.
- Programming Skills: Proficiency in Python or similar languages for coding.
- Statistical Analysis Understanding: Knowledge of data analysis and statistical methods.
- Interest in Financial Technology: Enthusiasm for applying AI to solve financial challenges.
Course Outline:
Lesson 1: Introduction to AI Agents in Finance
- 1.1 Understanding AI Agents in Finance vs Traditional Financial Automation
- 1.2 The Evolution of AI Agents in Financial Services
- 1.3 Overview of Different Types of AI Agents in Finance
- 1.4 Importance of Agent Autonomy and Task Delegation in Financial Settings
- 1.5 Key Differences Between AI Agents in Finance and Traditional Automation
- 1.6 Hands-On Activity: Exploring AI Agents in Finance
Lesson 2: Building and Understanding AI Agents in Finance
- 2.1 Architecture of AI Agents in Finance
- 2.2 Tools and Libraries for Agent Development
- 2.3 AI Agents vs. Static Models
- 2.4 Overview of Agent Lifecycle
- 2.5 Use Case: Customer Support Agents in Banks for Handling KYC, FAQs, and Transaction Disputes
- 2.6 Case Study: Bank of America’s Erica: A Virtual Financial Assistant that Handles 1+ Billion Interactions Using Predictive AI
- 2.7 Hands-On Activity: Building and Understanding AI Agents in Finance
Lesson 3: Intelligent Agents for Fraud Detection and Anomaly Monitoring
- 3.1 Supervised/Unsupervised ML for Fraud Detection
- 3.2 Pattern Analysis & Behavioural Profiling
- 3.3 Real-time Monitoring Agents
- 3.4 Real-World Use Case: AI Agents Monitoring Transaction Behaviour and Flagging Anomalies for Real-Time Fraud Detection in Digital Wallets
- 3.5 Case Study: PayPal’s AI System Uses Graph-Based Anomaly Detection Agents to Flag 0.32% of All Transactions for Fraud with 99.9% Accuracy
- 3.6 Hands-On Activity: Intelligent Agents for Fraud Detection and Anomaly Monitoring
Lesson 4: AI Agents for Credit Scoring and Lending Automation
- 4.1 Feature Generation from Non-Traditional Credit Data
- 4.2 Explainability (XAI) in Credit Decisions
- 4.3 Bias Mitigation in Lending Agents
- 4.4 Real-World Use Case: Agents Assessing New-to-Credit Individuals Using Transaction and Mobile Data
- 4.5 Case Study: Upstart’s AI-Based Lending Platform Approved by CFPB Showed 27% Increase in Approval Rate and 16% Lower APRs for Borrowers
- 4.6 Hands-On Activity: AI Agents for Credit Scoring and Lending Automation
Lesson 5: AI Agents for Wealth Management and Robo-Advisory
- 5.1 Personalization Using Profiling Agents
- 5.2 Portfolio Rebalancing Algorithms
- 5.3 Sentiment-Aware Investing
- 5.4 Real-World Use Case: AI Agent Adjusting Portfolio Weekly Based on Financial Goals and Market Trends
- 5.5 Case Study: Wealthfront’s Path Agent Uses Financial Behavior Modeling to Recommend Personalized Savings Goals and Investment Paths
- 5.6 Hands-On Activity: AI Agents for Wealth Management and Robo-Advisory
Lesson 6: Trading Bots and Market-Monitoring Agents
- 6.1 Reinforcement Learning in Trading Agents
- 6.2 Predictive Modelling Using Historical Data
- 6.3 Risk-Reward Threshold Management
- 6.4 Real-World Use Case: AI Trading Agents Performing Arbitrage Between Crypto Exchanges
- 6.4 Case Study: Renaissance Technologies Utilizes AI to Automate Short-Hold Trades, Generating Consistent Alpha via Adaptive Trading Bots
- 6.5 Hands-On Activity: Trading Bots and Market-Monitoring Agents
Lesson 7: NLP Agents for Financial Document Intelligence
- 7.1 LLMs in Earnings Call and Filings Analysis
- 7.2 AI Summarization and Event Detection
- 7.3 Voice-to-Text and Key-Point Extraction
- 7.4 Real-World Use Case
- 7.5 Case Study: BloombergGPT — A Financial-Grade Large Language Model
- 7.6 Hands-On Activity: NLP Agents for Financial Document Intelligence
Lesson 8: Compliance and Risk Surveillance Agents
- 8.1 AI for Anti-Money Laundering (AML) and Know Your Business (KYB)
- 8.2 Regulation-aware Rule Modelling
- 8.3 Transaction Graph Analysis
- 8.4 Real-World Use Case: Agent tracking suspicious cross-border money transfers in real-time across multiple accounts.
- 8.5 Case Study: HSBC uses Quantexa’s AI agents to trace AML networks, increasing suspicious activity detection by 30%.
- 8.6 Hands-On Activity: Compliance and Risk Surveillance Agents in Financial Systems
Lesson 9: Responsible, Fair & Auditable AI Agents
- 9.1 Governance Frameworks for AI in Finance (RBI, EU AI Act)
- 9.2 Transparency and Auditability in Decision Logic
- 9.3 Fairness and Explainability
- 9.4 Real-World Use Case: Auditable AI Agent Logs Used During Internal Policy Audits to Ensure Fair Lending practices.
- 9.5 Case Study: Wells Fargo implemented internal AI fairness reviews for lending bots post regulatory scrutiny.
- 9.6 Hands-On Activity: Responsible, Fair & Auditable AI Agents in Finance
Lesson 10: World Famous Case Studies
- 10.1 Case Study 1: JPMorgan’s COiN Platform
- 10.2 Case Study 2: AI in Fraud Detection – PayPal’s Decision Intelligence
- 10.3 Case Study: AI-Driven Credit Scoring – Upstart’s Lending Platform
- 10.4 Capstone Project
- 10.5 Key Takeaways of the Lesson
