Using Intermarket Data to Evaluate the Efficient Market Hypothesis with Machine Learning

Paper: arXiv 2212.08734

Authors: N’yoma Diamond, Grant Perkins

Abstract

In its semi-strong form, the Efficient Market Hypothesis (EMH) implies that technical analysis will not reveal any hidden statistical trends via intermarket data analysis. If technical analysis on intermarket data reveals trends which can be leveraged to significantly outperform the stock market, then the semi-strong EMH does not hold. In this work, we utilize a variety of machine learning techniques to empirically evaluate the EMH using stock market, foreign currency (Forex), international government bond, index future, and commodities future assets. We train five machine learning models on each dataset and analyze the average performance of these models for predicting the direction of future S&P 500 movement as approximated by the SPDR S&P 500 Trust ETF (SPY). From our analysis, the datasets containing bonds, index futures, and/or commodities futures data notably outperform baselines by substantial margins. Further, we find that the usage of intermarket data induce statistically significant positive impacts on the accuracy, macro F1 score, weighted F1 score, and area under receiver operating characteristic curve for a variety of models at the 95% confidence level. This provides strong empirical evidence contradicting the semi-strong EMH.

Complexity vs Empirical Score

• Math Complexity: 3.5/10
• Empirical Rigor: 6.8/10
• Quadrant: Street Traders — practical and empirical, lighter on theory

Why this score: The paper relies on standard machine learning models and statistical hypothesis testing rather than deep mathematical derivations, putting math complexity on the lower end. However, it demonstrates solid empirical rigor through multi-asset intermarket analysis, clear metric evaluation (F1, ROC-AUC), and statistical significance testing at the 95% confidence level.

Research Flowchart

  flowchart TD
    A["Research Goal: Test Semi-Strong EMH via Intermarket Machine Learning"] --> B["Data Collection: SPY, Forex, Government Bonds, Index & Commodities Futures"]
    B --> C["Feature Engineering: Technical Analysis & Intermarket Indicators"]
    C --> D["Model Training: Train 5 ML Classifiers to Predict SPY Direction"]
    D --> E["Performance Evaluation: Accuracy, F1 Scores & ROC-AUC vs. Baselines"]
    E --> F["Outcome: Bonds, Index & Commodities Data Outperform Baselines (p < 0.05)"]
    F --> G["Conclusion: Statistically Significant Trends Found — Semi-Strong EMH Rejected"]