AI for Finance Course

Lesson 1 • The Financial Data Landscape

Surveys the types, sources, and quality issues of financial data. Prepares learners to evaluate data suitability for AI projects.

Lesson 2 • AI Development Lifecycle in Finance

Outlines the end-to-end process from problem framing to model deployment. Anchors later chapters within a repeatable project framework.

Lesson 3 • What AI Means for Finance

Defines AI, machine learning, and deep learning in plain terms. Connects each concept to tangible financial workflows and decision points.

Lesson 1 • Cleaning and Handling Missing Values

Addresses outliers, duplicates, and gaps common in financial time series. Ensures data integrity before feature engineering begins.

Lesson 2 • Splitting and Avoiding Data Leakage

Explains time-aware train-test splits and look-ahead bias risks. Prevents inflated performance estimates that mislead production decisions.

Lesson 3 • Feature Engineering for Finance

Transforms raw financial variables into predictive signals. Directly improves model accuracy in subsequent chapters.

Lesson 4 • Sourcing and Ingesting Financial Data

Covers APIs, data vendors, and internal systems as data sources. Establishes reliable ingestion patterns for downstream processing.

Lesson 1 • Hyperparameter Tuning and Regularisation

Teaches grid search, random search, and regularisation to optimise models. Reduces overfitting common in noisy financial data.

Lesson 2 • Unsupervised Learning in Finance

Applies clustering and dimensionality reduction to segment clients and compress features. Extends analytical reach beyond labelled datasets.

Lesson 3 • Supervised Learning Fundamentals

Covers regression and classification algorithms with financial examples. Provides the algorithmic foundation for credit, pricing, and return models.

Lesson 4 • Model Evaluation and Metrics

Defines finance-relevant performance metrics beyond accuracy. Connects evaluation choices to business impact and risk tolerance.

Lesson 1 • Neural Network Fundamentals

Explains neurons, layers, activation functions, and backpropagation. Establishes the conceptual base for all deep learning architectures ahead.

Lesson 2 • Recurrent Networks for Time Series

Covers RNNs, LSTMs, and GRUs for sequential financial data modelling. Directly applicable to price forecasting and volatility estimation.

Lesson 3 • Convolutional Networks for Financial Signals

Adapts CNNs to extract local patterns from price charts and tabular data. Broadens the toolkit for pattern recognition in market data.

Lesson 4 • Transformer Models and Attention

Introduces attention mechanisms and transformer architectures for finance. Enables processing of long sequences and cross-asset relationships.

Lesson 1 • Sentiment Analysis for Market Signals

Builds lexicon-based and ML-driven sentiment classifiers on financial text. Produces tradable sentiment scores linked to price movements.

Lesson 2 • Large Language Models in Finance

Applies pre-trained LLMs to summarisation, Q&A, and report generation. Accelerates analyst workflows and knowledge extraction at scale.

Lesson 3 • Text Preprocessing and Representation

Covers tokenisation, stopword removal, and embedding methods. Converts raw text into numerical inputs for downstream models.

Lesson 4 • Information Extraction and Knowledge Graphs

Extracts entities, relationships, and events from financial documents. Structures unstructured text into queryable knowledge representations.

Lesson 1 • Anti-Money Laundering with AI

Applies network analysis and behavioural models to flag suspicious activity. Reduces manual review burden while meeting regulatory expectations.

Lesson 2 • Model Risk in Risk AI Systems

Addresses validation, documentation, and governance of risk models. Ensures AI-driven risk tools meet internal and regulatory standards.

Lesson 3 • Credit Risk Modelling with ML

Replaces scorecard methods with gradient boosting and neural models. Improves default prediction accuracy while maintaining interpretability.

Lesson 4 • Fraud Detection Systems

Builds real-time anomaly and classification models for transaction fraud. Balances detection rates against false positive costs in production.

Lesson 1 • Portfolio Optimisation with AI

Extends mean-variance optimisation with ML-estimated inputs and constraints. Produces more robust portfolios under realistic market conditions.

Lesson 2 • Reinforcement Learning for Trading

Applies RL agents to dynamic order execution and portfolio rebalancing. Introduces adaptive decision-making beyond static rule-based systems.

Lesson 3 • Backtesting and Strategy Evaluation

Implements rigorous backtesting frameworks to assess strategy viability. Guards against overfitting and survivorship bias in historical tests.

Lesson 4 • Algorithmic Trading Fundamentals

Covers order types, market microstructure, and execution mechanics. Provides the trading context needed to deploy AI signals responsibly.

Lesson 1 • Regulatory Expectations for AI in Finance

Maps global regulatory themes around model risk, transparency, and accountability. Prepares learners to engage with supervisors and internal audit teams.

Lesson 2 • AI Governance Frameworks

Structures policies, roles, and controls for responsible AI deployment. Translates regulatory expectations into operational governance practices.

Lesson 3 • Fairness and Bias in Financial AI

Identifies sources of bias in credit and insurance models and applies mitigation techniques. Aligns AI outputs with fair lending and anti-discrimination principles.

Lesson 4 • Privacy, Security, and Data Ethics

Addresses data minimisation, differential privacy, and adversarial attacks. Protects customer data and model integrity in production systems.