- The AI Finance Frontier
- Posts
- Granular Betas and Risk Premium Functions
Granular Betas and Risk Premium Functions
Generalizing up- and down-side betas to multi-factor functional measures of covariation
In partnership with
Hi! Here's Iván with this week's exciting newsletter, brimming with insights and discoveries on building robust investment strategies and risk models using Machine Learning.
In this edition, I am presenting the following sections:
🕹️ AI-Finance Insights: I summarize three must-read academic papers that mix cutting-edge ML/DL with Asset Pricing & Quant Finance:
Granular Betas and Risk Premium Functions
Structural Deep Learning in Conditional Asset Pricing
💊 AI Essentials: Today, I'm thrilled to share a user-friendly guide on how to use PCA and RSI for effective trading strategies.
🥐 Summer Book Recommendations: Summer recommendations for Algorithmic Trading.
🥐 Asset Pricing Insights: In this edition, I summarize a paper on the predictive ability of the Option Volume Imbalance (OVI).
Today’s Sponsor
Become an AI-Powered Finance Decisions to get 10x ROI on your money (free AI masterclass) 🚀
More than 300 million people use AI, but less than 0.03% use it to build investing strategies. And you are probably one of them.
It’s high time we change that. And you have nothing to lose – not even a single $$
Rated at 9.8/10, this masterclass will teach how you to:
Do market trend analysis & projections with AI in seconds
Solve complex problems, research 10x faster & make your simpler & easier
Generate intensive financial reports with AI in less than 5 minutes
Build AI assistants & custom bots in minutes
“ Granular Betas and Risk Premium Functions”
The paper introduces Granular Betas, a revolutionary approach for enhancingasset pricing models by capturing more detailed risk dependencies.
Granular Betas refine traditional beta measures to provide a more accurate assessment of local covariation between asset returns and risk factors, leading to new insights into risk premium functions.
The main contributions and findings are as follows:
👉 Granular Betas generalize up- and down-side betas to multi-factor functional measures of covariation, offering a more refined understanding of systematic risk exposures across the entire support of the factor.
👉 Implementing granular versions of the CAPM and Fama-French models with U.S. equity returns from 1963 to 2020 significantly outperforms traditional non-granular models. For example, the out-of-sample R2 for the granular CAPM is 3.8%, compared to 3.1% for the non-granular CAPM.
👉 The risk premium functions for various factors show significant non-linear dependencies, with market risk premiums particularly high for left-tail returns. This highlights that downside tail risk is priced more dearly by investors.
👉 Different stocks, such as technology and utility stocks, exhibit distinct expected return functions under granular betas, capturing more detailed risk-return relationships than traditional models.
👉 The study finds that risk premium functions vary with financial conditions. For instance, market risk premiums are higher during high financial uncertainty and in down markets. The size premium is more pronounced in down markets, while the value premium shows significant non-linearity under high uncertainty.
👉 Allowing for joint dependencies between factors through multi-dimensional partitions further enhances model performance, with the out-of-sample R2 for the granular CAPM improving from 3.8% to 4.8%.
“Structural Deep Learning in Conditional Asset Pricing”
The paper presents a novel econometric method for interpreting asset return predictions from deep neural networks (DNNs) in cross-sectional asset pricing.
The main contributions and findings are as follows:
👉 Opening the Black Box: The study provides a theoretical framework that decomposes DNN predictions into mispricing (alpha) and risk-related components (beta), enhancing the interpretability of machine learning models in finance.
👉 The authors develop formal asymptotic theory for neural network estimators, demonstrating their statistical properties and convergence behaviors in the context of asset pricing.
👉 By embedding neural network predictions into a factor pricing framework, the method aligns machine learning outputs with traditional asset pricing theory, making predictions more economically meaningful.
👉 The research shows that period-by-period training of neural networks can recover factor realizations and improve out-of-sample forecasts, while pooled machine learning is better for pure forecasting applications but less interpretable.
Sponsor 👇
Learn AI in 5 Minutes a Day
AI Tool Report is one of the fastest-growing and most respected newsletters in the world, with over 550,000 readers from companies like OpenAI, Nvidia, Meta, Microsoft, and more.
Our research team spends hundreds of hours a week summarizing the latest news, and finding you the best opportunities to save time and earn more using AI.
AI-Essentials
📹 A user-friendly guide on how to use PCA (Principal Component Analysis) and RSI (Relative Strength Index) for effective trading strategies. The tutorial includes easy-to-follow code examples, making it great for those looking to improve their trading methods with these techniques. 👇
Summer Books
(1) Hands-On Financial Trading with Python by Jiri Pik & Sourav Ghosh
Ideal for Python beginners in trading.
Academic: ⭐⭐ | Practical: ⭐⭐⭐
(2) Python for Algorithmic Trading by Yves Hilpisch
Basic introduction, practical for intermediate users.
Academic: ⭐⭐ | Practical: ⭐⭐⭐⭐
(3) Mastering Python for Finance by James Ma Weiming
Blends finance principles with Python.
Academic: ⭐⭐⭐⭐ | Practical: ⭐⭐⭐
(4) Machine Learning for Algorithmic Trading by Stefan Jansen
Extensive coverage on varied topics.
Academic: ⭐⭐⭐⭐ | Practical: ⭐⭐⭐
(5) In Pursuit of the Perfect Portfolio by Andrew Lo & Stephen Foerster
Focus on trading theories, based on Nobel Laureates' stories.
Academic: ⭐⭐ | Practical: ⭐⭐
(6) Machine Learning in Finance by Matthew Dixon, Igor Halperin, & Paul Bilokon
In-depth, graduate-level analysis of ML in finance.
Academic: ⭐⭐⭐⭐⭐ | Practical: ⭐⭐
(7) Day Trade With AI by Shunyu Tang
Theoretical and practical aspects of AI in trading.
Academic: ⭐⭐⭐ | Practical: ⭐⭐⭐⭐⭐
(8) Advances in Financial Machine Learning by Marcos Lopez de Prado
Cutting-edge exploration of ML applications in finance.
Academic: ⭐⭐⭐⭐⭐ | Practical: ⭐⭐⭐⭐
Asset Pricing Insights
“Option Volume Imbalance for Stock Market Predictions”
Strong empirical evidence supports the forecasting power of Option Volume Imbalance (OVI) in predicting stock and ETF returns.
We should consider incorporating OVI into any set of predictive inputs for ML/DL or other algorithmic approaches.
The paper, in a nutshell. 👇
➡ The research explores how imbalances in option trading volumes can predict future price movements in financial markets.
➡ By analyzing these imbalances through a nonlinear approach and categorizing market participants, the study uncovers strong indicators of future market returns happening overnight.
➡ The analysis identifies Market-Maker volumes as a crucial source of predictive signals, particularly emphasizing that options with high implied volatility, especially put options, have a greater predictive value than call options. The core of the paper is the examination of Option Volume Imbalance (OVI) and its connection to the future prices of stocks or ETFs.
➡ The findings demonstrate that OVI is a reliable predictor of the direction of asset prices over the next day.
➡ The study innovatively demonstrates how Option Volume Imbalances (OVIs) from various market participants contribute unique insights to the market, and further investigates how different characteristics of options influence the predictive strength of OVI for future stock returns.
➡ Finally, the paper also presents evidence of interconnected impacts across various stocks and ETFs in the market.
If you're enjoying our newsletter and want to support us, please recommend it to anyone you know who's interested in AI and Finance. Your referrals are the biggest compliment and help us grow! 🌟🤖💼