AI-Driven Trading and Data

This unit explores how machine learning and deep learning models are applied to stock trading and investment analytics, surveys new alternative data sources, and examines practical uses of generative AI like ChatGPT. It consolidates understanding of Chapters 6–10 through review exercises, highlights limitations and risk considerations, and prepares students to design and validate predictive investment models in subsequent units.

Learning Objectives

• Analyze the performance of algorithmic stock trading strategies by comparing backtest metrics (e.g., return, volatility, Sharpe ratio, maximum drawdown) across different models and datasets presented in the unit
• Apply machine learning and deep learning concepts to construct or outline a predictive investment model using new data sources, documenting feature selection, model architecture, training approach, and expected evaluation metrics
• Evaluate limitations, biases, and operational risks of AI-driven financial models—including data quality, model overfitting, explainability, and regulatory concerns—and propose concrete mitigation and validation strategies
• Demonstrate practical use of generative AI tools (e.g., ChatGPT) to automate research tasks, generate trade idea summaries, and synthesize findings from Chapters 6–10 by producing prompt logs, model outputs, and an actionable summary report