The Quantopian Podcast

In this episode of Quant Radio, we unpack a surprising twist in global markets: the US dollar fell sharply following the April 2025 tariff announcements—despite rising interest rates that should have strengthened it. Why did the textbook economics fail? We explore how shifting perceptions around US Treasuries, the "convenience yield" of dollar assets, and the deeper implications of trade policy might be signaling something more profound: a potential crack in the foundation of the dollar’s global dominance.We break down:- The "Dollar Disconnect" and what drove it- Why investors turned away from US Treasuries- The role of the convenience yield in currency strength- Historical lessons from past reserve currency shiftsIf you're wondering whether this is just market noise or the start of something much bigger, you won’t want to miss this episode.Find the full research paper here: https://community.quantopian.com/c/community-forums/dollar-upheaval-this-time-is-differentFor 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.

In this episode, we unpack a cutting-edge study tackling a key finance question: Should machine learning models treat all stocks the same—or consider industry differences? We break down three modeling strategies (generalist, specialist, hybrid) and reveal why blending industry context with big data may be the smartest move. From neural nets to sharp ratios, and from U.S. to global markets, we explore what really drives predictive performance. Spoiler: the hybrid wins. Whether you're a quant geek or just stock-curious, this one's for you.Find the full research paper here: https://community.quantopian.com/c/community-forums/do-machine-learning-models-need-to-be-sector-expertsFor 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.

Ever felt that itch when a stock soars or crypto headlines dominate your feed? That’s FOMO — and it might be moving markets worldwide. In this episode, we dive into the Global FOMO Index, a groundbreaking new way researchers are tracking investor sentiment through Google searches. Discover how global anxiety about "missing out" correlates with stock returns, volatility, and even political systems. It’s behavioral finance meets big data, with surprising insights on why hype can hurt — and how democracy might make it worse.Find the full research paper here: https://community.quantopian.com/c/community-forums/global-fomo-the-pulse-of-financial-markets-worldwideFor 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.

Discover the revival of a once-forgotten quant strategy, the two-period RSI, once dubbed the 'holy grail' of trading. Unpack its potential for mean reversion during market dips and how it's proven effective in bull markets. Learn about the thrills and perils of trading small-cap stocks, including the hidden risks of delisting. Explore refined strategies that balance risk while seeking success in larger stocks. Whether you're a seasoned trader or a curious novice, this deep dive offers invaluable insights into modern trading dynamics.

In this episode of Quant Radio, we explore one of the most fundamental questions in modern finance: When predicting stock returns, is it better to rely on global data or focus on local market insights? Backed by a massive 30-year dataset covering 45 markets and 147 stock characteristics, this discussion breaks down a compelling new study that uses machine learning—specifically, the Elastic Net model—to uncover whether broader data truly gives investors an edge. The results might surprise you. From analyzing abnormal returns and Sharpe ratios to identifying when global strategies outperform local ones (and why they often don’t), we uncover practical insights that could change how you approach investing. Whether you’re managing portfolios, researching market signals, or just fascinated by how data shapes financial decision-making, this episode brings clarity to the trade-off between complexity and precision. Dive in and discover where the real predictive power lies.Find the full research paper here: https://community.quantopian.com/c/community-forums/the-more-the-better-predicting-stock-returns-with-local-and-global-dataFor 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.

Artificial intelligence is reshaping the landscape of quantitative investment. In this video, we explore the shift from traditional quant models to AI-driven approaches, covering how deep learning and large language models (LLMs) are revolutionizing the way investors generate alpha, manage risk, and execute trades.We delve into how deep learning models—like convolutional neural networks, transformers, and graph neural networks—are being used to uncover complex patterns in financial data. You'll also see how reinforcement learning is being applied to optimize decision-making in dynamic market environments.The video also highlights the growing role of LLMs in finance. These models can process vast amounts of unstructured data, generate novel alpha signals, and even function as AI agents within the investment process. But while the potential is exciting, we also address the key limitations, including issues with interpretability, overfitting, market frictions, and the numerical reasoning gaps still present in current LLMs.Whether you're a quant, a data scientist, or just curious about how AI is changing the future of investing, this video offers a thoughtful and balanced look at one of the most transformative trends in finance today.Find the full research paper here: https://community.quantopian.com/c/community-forums/from-deep-learning-to-llms-a-survey-of-ai-in-quantitative-investmentFor 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.

In this video, we explore the design of a volatility trading system that blends two quantitative options strategies with a strong emphasis on risk management. The first strategy takes a long-short position in straddles, based on signals from the implied volatility term structure, aiming to exploit short-term dislocations. The second strategy involves selling out-of-the-money (OTM) puts, but only when the absorption ratio suggests stable market conditions—helping to avoid exposure during periods of systemic risk.The video also walks through how these strategies are combined using Equal Risk Contribution (ERC) to balance their risk inputs, and how a Constant Proportion Portfolio Insurance (CPPI) overlay helps protect the system from large drawdowns. Historical data and real-world events like the 2008 crisis and COVID crash are used to highlight both the strengths and limitations of each approach.If you’re interested in systematic trading, options strategies, or risk-adjusted portfolio design, this breakdown offers a clear, research-based perspective on how to use volatility both as a source of return and a signal for risk control.Find the full research paper here: https://community.quantopian.com/c/community-forums/volts-a-volatility-based-trading-system-to-forecast-stock-markets-trend-using-statistics-and-machine-learningFor 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.

Discover a fast, adaptive trend following strategy built specifically for NQ futures using the power of Kalman Filters. In this video, we explore how this innovative approach goes beyond traditional moving averages by filtering out market noise and dynamically tracking price trends. You’ll learn how the Quantitative Trend Indicator (QTI) is constructed using both fast and slow Kalman Filters to generate clear entry and exit signals.We walk through the exact trading rules, review detailed backtest results from 2017 to 2024, and examine how the strategy performed both before and after optimization. With high-frequency execution—up to 16 trades per day—the potential is eye-catching: strong annualized returns, reduced drawdowns, and a Sharpe ratio that outperforms the benchmark.But it’s not all upside. The video also dives into the real-world frictions that can erode theoretical performance, like execution speed, slippage, and transaction costs. We discuss those risks honestly and look at possible next steps for improving or adapting the system to other markets and timeframes.If you’re interested in algorithmic trading, quant strategies, or just want to understand how Kalman Filters can be applied to financial markets, this is one you won’t want to miss. Subscribe for more insights into advanced trading systems, performance analytics, and practical challenges in turning code into edge.Find the full research paper here: https://community.quantopian.com/c/community-forums/fast-trend-followingFor 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.#TrendFollowing #QuantTrading #KalmanFilter #NQFutures #Backtesting #AlgoTrading

For decades, the prevailing wisdom in finance has told us that higher risk equals higher reward. But what if that model is missing the most powerful driver of asset prices—human emotion? In this thought-provoking episode of Quant Radio, we explore the groundbreaking ideas of Robert D. Arnott and Edward F. McQuarrie, who argue that fear—not risk—is the real force shaping the markets. Drawing on historical data and behavioral insights, they challenge traditional models like CAPM and introduce their "Deranged Asset Pricing Model" (DAPM), which places investor psychology, especially fear of loss and fear of missing out (FOMO), at the heart of market movements. From meme stocks to bond yields, and even long-term equity underperformance, this episode offers a fresh, emotionally intelligent lens on why markets behave the way they do. Whether you're an investor, economist, or just curious about the inner workings of the financial world, this discussion will change the way you think about risk—and fear.Find the full research paper here: https://community.quantopian.com/c/community-forums/fear-not-risk-explains-asset-pricing-quantpediaFor 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.

In this video, we examine fascinating new research that uses machine learning to uncover hidden connections between global stock markets and US equities. The study reveals how artificial intelligence can detect predictive signals from foreign markets that influence US stocks - including companies with no obvious international exposure.The research team analyzed an enormous dataset spanning 47 foreign markets, employing advanced machine learning techniques like Lasso regression, Random Forests, Gradient Boosting, and Neural Networks. These models processed over 13,000 potential signals from both market-level and individual stock returns to identify meaningful patterns.One of the most surprising findings was the predictive power of signals from unexpected markets like Qatar, challenging conventional wisdom about which foreign markets matter most. The study also uncovered intriguing dynamics around information diffusion, showing that foreign signals tend to be more predictive when they receive less US media coverage, and that the full impact of global information on US stocks can take 5-8 weeks to materialize.While the best-performing models generated impressive hypothetical returns of 14.2% annualized, the research highlights significant practical challenges. High trading costs from frequent portfolio adjustments, the inherent "black box" nature of complex machine learning models, and the evolving efficiency of global markets all present hurdles for real-world implementation.The discussion concludes by considering the broader implications of these findings for market efficiency and the future of AI in finance. As machine learning tools become more sophisticated, will they eliminate these informational edges or simply uncover new layers of market complexity?