This course develops a framework to build and analyze quantitative investment strategies. We will take advantage of recent innovations in AI and extensively use large language models such as those developed by Anthropic, Google, and OpenAI (and related models). You will get an in-depth understanding and hands-on experience how these tools are incredibly useful in quantitative portfolio management (and in the asset management industry at large), and how they can transform the industry in the future.
We will use the AI models to develop code to analyze big data (such as stock prices and returns, firm fundamentals, text data, portfolio holdings and flows) for the purpose of predicting returns, measuring risk, estimating firm valuations, and ultimately building investment strategies. The final project requires you to develop and pitch a new investment strategy using this framework. The course will use Python as a coding language, but no prior knowledge of Python is required for this course.
The course starts with a brief review of the traditional portfolio choice framework introduced in the Investments course and then covers much of the recent research on quantitative methods to build and critically analyze investment strategies.
Key topics covered in the course are:
- An overview of recent developments in the asset management industry related to active vs passive investing, institutional vs retail investors (including high net worth individuals and family offices), and sustainable investing.
- Recent innovations in quantitative investing, such as factor investing, and industry applications via fundamental indexing and smart-beta products. We will also discuss how macroeconomic conditions (e.g., inflation and monetary policy) impact the success of these strategies.
- Market frictions and the capacity of investment strategies, incentives of asset managers, and evaluating the performance of actively-managed strategies, with applications to ETFs, hedge funds, and mutual funds.
- AI/ML methods and big data in the asset management industry: Applications and insights from big data (including text, holdings, flows, and alternative data sources).
- Using quantitative methods for firm valuation, and how to connect and integrate different approaches to investing, such as fundamental/value investing and quantitative investing.
The lecture material is built around recent academic research, problem sets, case studies, and significant time is spent on current events.
