Paper: arXiv 2507.09347

Authors: Ivan Letteri

Abstract

Purpose: This study introduces a novel framework for identifying and exploiting predictive lead-lag relationships in financial markets. We propose an integrated approach that combines advanced statistical methodologies with machine learning models to enhance the identification and exploitation of predictive relationships between equities. Methods: We employed a Gaussian Mixture Model (GMM) to cluster nine prominent stocks based on their mid-range historical volatility profiles over a three-year period. From the resulting clusters, we constructed a multi-stage causal inference pipeline, incorporating the Granger Causality Test (GCT), a customised Peter-Clark Momentary Conditional Independence (PCMCI) test, and Effective Transfer Entropy (ETE) to identify robust, predictive linkages. Subsequently, Dynamic Time Warping (DTW) and a K-Nearest Neighbours (KNN) classifier were utilised to determine the optimal time lag for trade execution. The resulting strategy was rigorously backtested. Results: The proposed volatility-based trading strategy, tested from 8 June 2023 to 12 August 2023, demonstrated substantial efficacy. The portfolio yielded a total return of 15.38%, significantly outperforming the 10.39% return of a comparative Buy-and-Hold strategy. Key performance metrics, including a Sharpe Ratio up to 2.17 and a win rate up to 100% for certain pairs, confirmed the strategy’s viability. Conclusion: This research contributes a systematic and robust methodology for identifying profitable trading opportunities derived from volatility-based causal relationships. The findings have significant implications for both academic research in financial modelling and the practical application of algorithmic trading, offering a structured approach to developing resilient, data-driven strategies.

Complexity vs Empirical Score

  • Math Complexity: 8.5/10
  • Empirical Rigor: 6.0/10 (capped from 7.0: transaction costs only partially modelled; see penalty flags)
  • Quadrant: Holy Grail — high math complexity, high empirical rigor (effective empirical rigor capped from 7.0)

Why this score: The paper employs a sophisticated mathematical pipeline combining GMM clustering, multiple causal inference tests (Granger, PCMCI, Transfer Entropy), and DTW for lag optimization, indicating high mathematical density. While the backtest results show strong performance metrics and a defined testing period, the absence of publicly available code or datasets and reliance on a specific, short out-of-sample window slightly limits the empirical rigor compared to a fully reproducible study.

Research Flowchart

  flowchart TD
  A["Research Goal"] -->|"Identify lead-lag relationships"| B["Data Preprocessing"]
  B --> C["Variance Reduction<br>GMM Clustering"]
  C --> D["Reliability Assessment<br>Multi-stage Causal Pipeline"]
  D -->|"GCT, PCMCI, ETE"| E["Trade Signal Generation<br>DTW + KNN"]
  E --> F["Strategy Execution"]
  F --> G["Performance Evaluation"]
  
  style A fill:#e1f5fe
  style G fill:#e8f5e8
  style D fill:#fff3e0

Evidence Card

What the authors claim, on what data, and who has checked it. Read from the paper's own text by a language model: every quote is verbatim, nothing was re-run. How to read this card

Proposes

The paper proposes an integrated volatility‑based trading framework that combines statistical methods and machine learning to identify and exploit predictive lead‑lag relationships between equities.

Source sentence
We propose an integrated approach that combines advanced statistical methodologies with machine learning models to enhance the identification and exploitation of predictive relationships between equities.

Assumes 2

  • Trading incurs only a fixed commission of $9 per trade, with no slippage or bid‑ask spread considered. execution
    Source sentence
    with a fixed commission of $9 per trade and a fully compounded strategy.
  • The nine selected stocks are representative of broader market behavior for the purpose of volatility clustering. market
    Source sentence
    We employed a Gaussian Mixture Model (GMM) to cluster nine prominent stocks based on their mid-range historical volatility profiles over a three-year period.

Data

Backtest sample: 2023-06 – 2023-08 · US equities · equities · daily

  • Nine prominent stocks volatility dataset market-prices unknown
    three-year period (approximately 1 Nov 2 · nine well‑known stocks (e.g., TSLA, AMZN, META, MU, QCOM, INTC)
    Source sentence
    We employed a Gaussian Mixture Model (GMM) to cluster nine prominent stocks based on their mid-range historical volatility profiles over a three-year period.

Costs

Partial Costs appear only as a robustness check, a flat fee without spread or impact, or outside the headline numbers.

Fixed commission of $9 per trade; other costs such as slippage and spread are not modeled.

Source sentence
with a fixed commission of $9 per trade and a fully compounded strategy.

Finds 3

Reported performance (volatility-based causal directional trading): Sharpe 2.17 · total return 15.4%

  • The volatility‑based trading strategy achieved a total return of 15.38% over the 45‑day backtest, outperforming the 10.39% return of a buy‑and‑hold benchmark. performance
    Source sentence
    The portfolio yielded a total return of 15.38%, significantly outperforming the 10.39% return of a comparative Buy-and-Hold strategy.
  • The strategy attained a Sharpe Ratio up to 2.17 and a win rate up to 100% for certain stock pairs. performance
    Source sentence
    Key performance metrics, including a Sharpe Ratio up to 2.17 and a win rate up to 100% for certain pairs, confirmed the strategy's viability.
  • The MU → QCOM pair generated a 15.12% return with a 100% win rate and a Sharpe Ratio of 2.17. performance
    Source sentence
    Strategy MU →QCOM (2-day lag): Trading QCOM based on MU’s trend yielded a return of 15.12%. The strategy showed exceptional performance with

Checked by others

No other paper in the archive has been found to support or contradict these findings (compared with 16 related papers). Coverage is partial, so this is neither replication nor refutation.

Code

No repository by the authors found in the paper.

Extracted 2026-11-14 · same card as JSON · A language model chose these items: check the source sentence before relying on one.

Cited References (34)

  1. VolTS: A Volatility-based Trading System to forecast Stock Markets Trend using Statistics and Machine Learning — → 2307.13422
  2. VolTS Augmented: An Improvement of a Volatility-based Trading System to Forecast Stock Markets Trends (2024) — link
  3. DNN-ForwardTesting: A New Trading Strategy Validation using Statistical Timeseries Analysis and Deep Neural Networks (2022) — link
  4. Forecasting intraday volatility in the US equity market. Multiplicative component GARCH (2012) — link
  5. Pairs trading: Performance of a relative-value arbitrage rule (2006)
  6. How Crashes Develop: Intradaily Volatility and Crash Evolution (2019) — link
  7. Volatility and Correlation Forecasting (2006) — link
  8. K-Means++: The Advantages of Careful Seeding (2007)
and 26 more
  1. CHANGE DETECTION OF ORDERS IN STOCK MARKETS USING A GAUSSIAN MIXTURE MODEL (2014) — link
  2. Co-Integration and Error Correction: Representation, Estimation, and Testing (1987)
  3. Drift‐Independent Volatility Estimation Based on High, Low, Open, and Close Prices (2000)
  4. AITA: A new framework for Trading Forward Testing with an Artificial Intelligence Engine (2023) — link
  5. A Stock Trading System for a Medium Volatile Asset using Multi Layer Perceptron (2022) — link
  6. Imbalanced Dataset Optimization with New Resampling Techniques (2021) — link
  7. New Optimization Approaches in Malware Traffic Analysis (2021) — link
  8. Care Robots Learning Rules of Ethical Behavior Under the Supervision of an Ethical Teacher (Short paper) (2022) — link
  9. Logic-based Machine Learning for Transparent Ethical Agents (2020) — link
  10. A Logic-based Multi-agent System for Ethical Monitoring and Evaluation of Dialogues (2021) — link
  11. Feature Selection Strategies for HTTP Botnet Traffic Detection (2019) — link
  12. Causation, Prediction, and Search (2001) — link
  13. Causal inference in statistics: An overview (2009) — link
  14. Security in the internet of things: botnet detection in software-defined networks by deep learning techniques (2019) — link
  15. Dataset Optimization Strategies for MalwareTraffic Detection (2020) — link
  16. A Novel Resampling Technique for Imbalanced Dataset Optimization (2020) — link
  17. Stock Market Forecasting Using Machine Learning Models Through Volatility-Driven Trading Strategies (2024) — link
  18. Trading Strategy Validation Using Forwardtesting with Deep Neural Networks (2023) — link
  19. First Evaluation of an Adaptive Tool Supporting Formative Assessment in Data Science Courses (2023) — link
  20. The VIX index under scrutiny of machine learning techniques and neural networks (2021) — link
  21. High-Dimensional Granger Causality Tests with an Application to VIX and News* (2022) — link
  22. An Outlier Detection Algorithm based on KNN-kernel Density Estimation (2020) — link
  23. On Clustering Multimedia Time Series Data Using K-Means and Dynamic Time Warping (2007) — link
  24. Extension of constraint-procedural logic-generated environments for deep Q-learning agent training and benchmarking (2023) — link
  25. Selection of a Portfolio of Pairs Based on Cointegration: A Statistical Arbitrage Strategy (2013) — link
  26. High- Frequency and Model - Free Volatility Estimators (2009) — link

1 of 34 cited works are in the corpus; resolved via arXiv source bundles, Semantic Scholar and OpenAlex. Corpus-wide: 2596 linked papers.