Quant Radio: "Double Descent" in Portfolio Optimization

Ever wondered how many assets you should include in your investment portfolio? Conventional wisdom suggests that adding too many stocks leads to overfitting, but what if that’s not the full story? In this episode, we dive into groundbreaking research on double descent, a phenomenon that challenges traditional beliefs about portfolio complexity. We explore the surprising link between investing and machine learning, uncover why adding more assets—even beyond your data points—might actually improve performance, and break down the balance between Sharpe ratios, estimation error, and statistical mechanisms. Using over 50 years of U.S. stock market data, we examine how this theory plays out in the real world and what it means for portfolio construction, risk management, and even AI-driven investing. This discussion will make you rethink everything you thought you knew about building a portfolio. Tune in and discover why complexity might just be your portfolio’s best friend!

Find the full research paper here: https://community.quantopian.com/c/community-forums/double-descent-in-portfolio-optimization-dance-between-theoretical-sharpe-ratio-and-estimation-accuracy

For more quant-focused content, join us at ⁠⁠⁠⁠https://community.quantopian.com⁠⁠⁠⁠. There, you can explore a wealth of resources, connect with fellow quants, engage in insightful discussions, and enhance your skills through our extensive range of online courses.

Quant Radio is an AI-generated podcast, intended to help people develop their knowledge and skills in Quant finance. This podcast is not intended to provide investment advice.