Skip to content
All library documents

Finding Equity Lead-Lag Trades with Volatility Clustering and Causal Tests

Article arXiv papers · Author: Ivan Letteri
Read the original

Summary

The study presents a pipeline for finding directional trading signals from relationships between nine stocks. It first groups stocks by historical mid-range volatility with a Gaussian Mixture Model, then tests for predictive links using Granger causality, a customized PCMCI procedure, and effective transfer entropy. Dynamic Time Warping and a K-Nearest Neighbours classifier are used to estimate the lag at which a signal might be traded. The resulting strategy is evaluated through backtesting.

For the period from 8 June to 12 August 2023, the reported portfolio return was 15.38%, compared with 10.39% for buy and hold. The paper also reports a Sharpe ratio as high as 2.17 and win rates up to 100% for some pairs. These results are limited to the stated stocks and short test period; the summary does not describe transaction costs, out-of-sample validation beyond that period, or robustness across market regimes. The reported performance therefore illustrates the pipeline's potential rather than establishing that its signals will generalize.

Key ideas

  • Stocks are grouped by historical volatility before candidate predictive relationships are tested.
  • Granger causality, a customized PCMCI test, and effective transfer entropy form a multi-stage link-screening process.
  • Dynamic Time Warping and K-Nearest Neighbours are used to estimate signal-to-trade timing.
  • The reported backtest exceeded buy and hold over its short stated evaluation window.
  • The limited test period and unspecified implementation details constrain conclusions about generalization.

Tags

EquitiesVolatilityStatisticsMachine learningBacktesting
Full text
# A Framework for Predictive Directional Trading Based on Volatility and Causal Inference


# A Framework for Predictive Directional Trading Based on Volatility and Causal Inference









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.

Shown in full with attribution under the source's licence. Licence: abstract CC0

This summary was written by Stratmill's research agent from the original; it is not a copy of the source.