Deep Learning for Options Trading

End-To-End Machine Learning strategy for options trading

August 16, 2024

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 two must-read academic papers that mix cutting-edge ML/DL with Asset Pricing & Quant Finance:

    • Deep Learning for Options Trading: An End-To-End Approach

    • What If Option Closing Prices Were Trustworthy? A Machine Learning Approach

  • 💊 AI Essentials: The section on top AI & Quant Finance learning resources. Today, I present 5 essential books for starting with machine learning, statistics, and quant finance.

  • 🥐 Asset Pricing Insights: In this edition, I provide a method to combine short-term reversal and trading volume to enhance any short-term momentum-based strategy.

Today’s Sponsor

We put your money to work

Betterment’s financial experts and automated investing technology are working behind the scenes to make your money hustle while you do whatever you want.

“Deep Learning for Options Trading: An End-To-End Approach”

The paper introduces a nice ML strategy for options trading, moving beyond traditional market dynamics and option pricing models by employing a fully integrated neural network framework.

The main contributions and findings are as follows:

👉 The study presents an end-to-end neural network that directly learns optimal trading decisions from market data, bypassing the need to predict option returns or simulate market processes. This approach is specifically applied to a portfolio of delta-neutral equity options.

👉 Backtesting results over a decade reveal that deep learning models, particularly Linear and LSTM models, significantly outperform traditional trend-based strategies, achieving Sharpe ratios as high as 1.329.

👉 The research further shows that incorporating turnover regularization enhances model performance, maintaining profitability even under high transaction costs, thereby proving the robustness and efficiency of this innovative approach.

“What If Option Closing Prices Were Trustworthy? A Machine Learning Approach”

The paper addresses the challenge of determining accurate closing prices for equity options, which currently suffer from issues such as stale information and potential manipulation. The authors propose a machine learning model that leverages underlying stock prices from closing auctions to create a more reliable benchmark for option closing prices.

Their findings indicate significant deviations between traditional last-trade prices or 4 PM mid-quotes and their machine learning-generated benchmark, with deviations averaging 35% and 47%, respectively. The study demonstrates that the proposed machine learning models outperform traditional option pricing models, such as the Black-Scholes-Merton model, in terms of accuracy. The research suggests that implementing closing auctions for options, similar to those in equity markets, could enhance price efficiency and reliability in the options market.

Sponsor 👇

Better PR with minimal effort: Let AI write your articles

  • Generate high-quality articles in seconds - SEO-optimized, plagiarism & fact-checked

  • Be featured for free by journalists looking for credible sources and build authority

  • Get your articles indexed and ranked directly in Google News

  • Distribute your content to top magazines with a single click

  • Forget about ChatGPT: Manage, publish and track your PR efforts in one place

Get great PR fast:

AI-Essentials

Five essential resources for starting with machine learning, statistics, and quant finance. Take a look at them! 👇

Asset Pricing Insights

“Short-term Momentum: Reversal vs Trading Volume”

Short-term reversal in momentum-related strategies is well-known. However, the short-term reversal is concentrated only on those stocks with low trading volumes.

Combining both facts substantially increases the effectiveness of any short-term reversal strategy.

Here, I summarize the paper in less than 2 min: 👇

➡ The study unveils a notable pattern in both U.S. and international stock markets, demonstrating how stocks' performance can be predicted by looking at the previous month's returns and trading volumes.

➡ It finds that stocks with low trading volumes tend to reverse their short-term trends, while those with high volumes continue to follow the momentum established in the short term. This momentum is found to be as lucrative and enduring as the traditional price momentum.

➡ Notably, this momentum effect persists even after accounting for transaction costs and is most pronounced among stocks that are large, liquid, and widely followed.

➡ The findings challenge traditional models based on strict rational market behavior, suggesting instead that they may be better explained by some traders not fully appreciating the informational value of stock prices.

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! 🌟🤖💼