Simplicity or Complexity? Rethinking Trading Models in the Age of AI and Machine Learning

In partnership with

When it comes to trading system design, there are two schools of thought: one advocates for simpler rules, while the other favors more complex ones. Which approach is better? This newsletter explores both perspectives through the lens of machine learning.

In this issue:

• Latest Posts

• Use of Machine Learning in Pairs Trading

  • Findings

• Can a Complex Trading System Be Profitable

  • Findings

• Closing Thoughts

• Further Reading

• Educational Video

  • Ernest Chan - Machine Learning for trading, AI Age …

• Volatility Weekly Recap

• Around the Quantosphere

Latest Posts

• Low-Volatility Stocks: Reducing Risk Without Sacrificing Returns (11 min)

• The Calendar Effects in Volatility Risk Premium (9 min)

• Stock-Bond Correlation: What Drives It and How to Predict It (10 min)

• Profitability of Dispersion Trading in Liquid and Less Liquid Environments (10 min)

• Machine Learning in Financial Markets: When It Works and When It Doesn’t (10 min)

Use of Machine Learning in Pairs Trading

Machine learning has become an essential tool in modern finance, transforming the way financial institutions and investors approach data analysis and decision-making.

Reference [1] explored the use of machine learning in pairs trading. Specifically, the authors developed an algorithm to trade the classic Pepsi/Cola pair using three predictive methods: (i) fitting a linear model to real datasets of Pepsi and Coca-Cola stocks, (ii) employing a neural network approach to fit non-linear models, and (iii) utilizing an error correction model (ECM).

Findings

• The study investigates the relationship between two correlated stocks, Pepsi and Coca-Cola, using regression modeling and machine learning algorithms.

• The data is split into a training set (75%) and a testing set (25%) to evaluate model performance.

• A simple linear relationship between Pepsi prices (Y) and Coca-Cola prices (X) is modeled using both ordinary least squares (OLS) and a neural network (NN).

• A non-linear model between Y and X was fitted using the neural network (NN) method, and predictions were made for the X series.

• Two co-integrated stationary processes are used to analyze trading performance: the spread (Y − 𝑌^) and the ratio (𝑌^/X).

• The performance of each strategy is evaluated to determine the most effective approach for trading based on the co-movement of Pepsi and Coca-Cola.

• The total profit was computed and compared: the linear model generated a profit of $1.05102, while the neural network model produced $1.049395.

• The NN model's performance was similar to that of the linear method.

• The NN model can outperform other methods if the optimal number of neurons is used in the hidden layers.

In short, the neural network performs similarly to the linear model method but can be improved by optimizing the number of neurons.

Reference

[1] R. Sivasamy, Dinesh K. Sharma, Sediakgotla, and B. Mokgweetsi, Machine Learning Algorithmic Model for Pairs Trading, in Machine Learning for Real World Applications, Springer 2024.

Can a Complex Trading System Be Profitable

The previous article shows that a more complex system does not lead to higher returns. Reference [2], however, demonstrates that such a complex system can provide better risk-adjusted performance. The authors achieved that by using Machine Learning techniques.

Findings

• Traditional financial literature often relies on simple models with few parameters to predict market returns.

• This study theoretically proves that such simple models significantly understate the potential for return predictability.

• The article provides new theoretical insights into the out-of-sample performance of machine learning portfolios.

• It demonstrates that high-complexity models in machine learning can improve investment strategies, contradicting conventional wisdom.

• Market timing strategies based on ridgeless least squares can generate positive Sharpe ratio improvements, even for highly complex models.

• The study shows that machine learning models can perform better with greater model parameterization, despite having fewer training observations and minimal regularization.

• The findings are supported by random matrix theory and explained through intuitive statistical mechanisms.

• The article argues that out-of-sample R² is a poor measure of a model's economic value, as models with large negative R² can still generate large economic profits.

• It recommends that the finance profession shift focus from forecast accuracy to evaluating models based on economic metrics, such as Sharpe ratios.

Reference

[2] Kelly, Bryan T., and Malamud, Semyon and Zhou, Kangying, The Virtue of Complexity in Machine Learning Portfolios (2023). Swiss Finance Institute Research Paper No. 21-90

Closing Thoughts

So, should a trading system be simple and intuitive or complex and data-rich? In this edition, we featured research supporting both schools of thought. Perhaps both approaches have merit, depending on the context and objectives. What ultimately matters is not the simplicity or complexity of the model, but whether it has been thoroughly tested, proven robust across different market conditions, and shown to deliver consistent profitability before risking real capital.

Further Reading

Check out past newsletters on Machine Learning in finance

Machine Learning in Financial Markets: When It Works and When It Doesn’t

Educational Video

Ernest Chan - Machine Learning for trading, AI Agents, Conditional Portfolio optimization

In this video, Dr. Ernest Chan explores the cutting edge of machine learning and AI in finance. He shares valuable insights on building robust data pipelines, engineering predictive signals, and selecting appropriate machine learning models for live trading. The episode also covers practical risk management techniques, dynamic position sizing, and the emerging role of AI agents in asset management.

Volatility Weekly Recap

The figure below shows the term structures for the VIX futures (in colour) and the spot VIX (in grey).

The S&P 500 started Monday with a volatile session after Moody’s downgraded the US credit rating. The market sold off again on Friday due to renewed tariff tensions. Overall, large-cap stocks lost 2.46%, mid-cap stocks dropped 3.21%, and small-cap stocks fell 3.6%. Crypto had a big week, with Bitcoin reaching a new all-time high above $111,000. Gold prices jumped, and Treasury yields climbed.

On the volatility front, the VIX term structure shifted from contango last week to backwardation in the middle portion of the curve. The roll yield ended near zero, moving from positive to almost flat.

This resulted in returns of 13.43% and 6.67% for VXX and VIXM respectively.

Around the Quantosphere

• The Highest Paying Internships in America 2025 (universitymagazine)

• Citadel's CTO says AI won't generate lasting alpha for hedge funds (efinancialcareers)

• Ex-JPMorgan Analyst Builds a 51%-a-Year Quant Powerhouse in Taiwan (bloomberg)

• Another DeepSeek? Chinese quant fund publishes paper on AI training breakthrough (scmp)

• How hedge fund ‘Ronaldos’ beat the Trump slump (fnlondon)

• Can anything stop America’s superstar hedge funds? (economist)

• Hedge funds ramp up CLO market activity amid strong loan demand (hedgeweek)

• Bond Investors Threaten Popular Hedge-Fund Bet on Swap Spreads (bloomberg)

Disclaimer

This newsletter is not investment advice. It is provided solely for entertainment and educational purposes. Always consult a financial professional before making any investment decisions.

We are not responsible for any outcomes arising from the use of the content and codes provided in the outbound links. By continuing to read this newsletter, you acknowledge and agree to this disclaimer.