Month: May 2026

Volatility Derivatives and VIX Market Dynamics

Hedging is a fundamental risk management tool. The most common hedging instruments are futures and options associated with a given underlying asset, when available. For equity exposure, index options are also widely used for hedging.

However, hedging can be done not only through equity index options, but also through volatility derivatives, although the latter are considerably more complex and nuanced. In this post, we discuss the evolving dynamics of VIX futures and volatility ETPs, including lead-lag relationships, price discovery, and how hedging flows can influence volatility markets across different regimes and trading periods.

Lead-Lag Relationship Between the VIX Index and VIX Futures

The volatility index, VIX, is a measure of the stock market’s expectation of volatility over the next 30 days. The VIX index is calculated by taking a weighted average of the prices of put and call options on the S&P 500 index. The VIX is sometimes referred to as the “fear index” because it tends to spike when investors are worried about a sudden drop in the stock market.

VIX futures are derivative contracts that allow investors to bet on the direction of the VIX.  They are traded on the Chicago Board Options Exchange (CBOE). VIX futures were first introduced in 2004, and they are now one of the most popular derivatives contracts. VIX futures are traded in monthly contracts, and each contract represents a bet on the direction of the VIX index at the end of the contract month.

Reference [1] examined the lead-lag relationship between the VIX index and VIX futures. It utilized the symmetric thermal optimal path (TOPS) method that can handle non-stationary time series.

Findings

-The study examines the dynamic lead-lag relationship between the VIX and VIX futures markets using the symmetric thermal optimal path (TOPS) method.

-The results show that the VIX dominated VIX futures during the early years, particularly before the introduction of VIX options.

-In most periods, the relationship alternates rather than showing persistent dominance by one market.

-During the initial phase, VIX futures typically lagged the VIX by less than five days.

-The weaker role of VIX futures in the early period is attributed to lower trading volume.

-The importance of VIX futures in price discovery increases over time, especially after the launch of VIX options in 2006 and VIX ETPs in 2009.

-Since 2006, the lead-lag relationship has alternated, with the VIX sometimes leading futures and futures sometimes leading the VIX.

-The growth of VIX derivatives markets appears to have increased the informational efficiency of VIX futures.

Briefly, in the early days, the VIX index led its futures. However, the dynamics have changed; VIX futures now sometimes lead the spot market. This could be explained by the launch of VIX options and Exchange-Traded Notes.

Reference

[1] Yan-Hong Yang and Ying-Hui Shao, Time-dependent lead-lag relationships between the VIX and VIX futures markets, 2019, arXiv:1910.13729

Intraday Elasticity Between VIX Futures and Volatility ETPs

Reference [2] analyzes the sensitivity of VIX ETPs to movements in VIX futures. Specifically, the authors investigate the intraday price dynamics of the SPVXSTR, along with three VIX ETNs (VXX, XIV, TVIX) and three ETFs (VIXY, SVXY, UVXY), all linked to that index. Rather than relying on standard OLS regression, the study employs quantile regression, which minimizes a weighted sum of absolute errors and allows for asymmetric penalties on over- and under-predictions.

Findings

-The study analyzes the elasticity of VIX futures to volatility ETP prices using decile regressions on the S&P 500 VIX Short-Term Total Return Index (SPVXSTR).

-The results show that elasticity is lower near market close but higher during intraday trading, likely reflecting liquidity differences.

-Elasticity increases at the extreme ends of the return distribution near the close.

-VXX exhibits significantly higher elasticity than VIXY, attributed to its dominant and largely unhedged note structure.

-XIV and SVXY display similar elasticity patterns, while TVIX shows roughly half the elasticity of UVXY due to its lower leverage.

-The findings suggest that intraday liquidity amplifies the responsiveness of VIX futures to ETP price movements.

-VIX futures are found to be more sensitive to VXX than to TVIX or XIV during most trading periods.

-Sensitivity to XIV increases throughout the trading day in higher-return environments, likely reflecting increased hedging demand.

-The study highlights that VIX futures may overreact to ETP flows during stress periods and volatile market closes.

In short, the results show that VIX futures (SPVXSTR) are generally more sensitive to VXX than to TVIX or XIV, with the exception of the late-afternoon window (3:45–4:15 p.m.). Intraday elasticity is elevated—especially near the close and in the tails—implying that VIX futures can overreact to ETP price changes, which creates potential trading opportunities and important considerations for hedging under stress.

Reference

[2] Michael O’Neill, Gulasekaran Rajaguru, Elasticity dynamics between VIX futures and ETPs: a quantile regression analysis of intraday and closing market behavior, Journal of Accounting Literature (2025) 47 (5): 694–701.

Closing Thoughts

Taken together, these studies highlight the evolving dynamics of volatility markets and the growing importance of VIX derivatives and ETPs in price discovery and market behavior. The evidence suggests that lead-lag relationships between the VIX and VIX futures are time-dependent and increasingly influenced by derivative products and hedging flows.

At the same time, the elasticity of VIX futures to ETP activity varies across volatility regimes and intraday periods, implying that liquidity conditions and dealer positioning can materially affect market dynamics. These findings are particularly relevant for volatility traders, portfolio managers, and risk managers operating in increasingly complex derivatives markets.

Overfitting and Parameter Selection in Trading Strategies

The risk of overfitting is serious and can lead to significant losses. It has been discussed in previous posts. In this edition, we revisit the topic, given its continued relevance to quantitative strategy development.

Formal Study of Overfitting in Trading System Design

A serious problem when designing a trading system is the overfitting phenomenon, wherein the system is excessively tuned to historical data. Overfitting occurs when a trading strategy performs exceptionally well on past data but fails to generalize to new, unseen data. This can lead to false positives and inflated expectations, as the system may appear profitable due to chance rather than true predictive power.

Reference [1] formally studied this issue, using analytical approximations for the in-sample and out-of-sample Sharpe ratios of portfolios.

Findings

-The paper analyzes how the in-sample performance of trading strategies based on linear predictive models deteriorates out-of-sample due to overfitting.

-It develops closed-form approximations for both in-sample and out-of-sample Sharpe ratios by modeling the means and variances of strategy PnLs.

-The results show that strategies using a large number of assets and weak signals experience a significant decline in out-of-sample performance.

-In contrast, strategies relying on fewer but stronger signals tend to exhibit more stable and replicable results.

-Increasing the size of the training dataset improves the out-of-sample replication ratio and reduces overfitting risk.

-Signals with low true Sharpe ratios are particularly prone to overfitting, leading to inflated in-sample performance that does not persist.

-Simulation and empirical studies, including applications to commodity futures, confirm the magnitude and robustness of these effects.

-The findings also show that incorporating more realistic signal dynamics does not materially alter the main conclusions.

-The replication ratio is largely determined by the true out-of-sample Sharpe ratio rather than specific model assumptions.

-Overall, the study suggests that controlling model complexity and maximizing data usage are key to mitigating overfitting in predictive trading strategies.

In summary, the paper formally demonstrated that to minimize the risk of overfitting, one should,

  1. Keep models as simple as possible,
  2. Use the longest sensible backtest period available,
  3. Develop systems with high Sharpe ratios, and
  4. Rely on fewer signals.

From our experience, we have reservations about points #3 and #4, while agreeing with points #1 and #2. What do you think?

Reference

[1] Antoine Jacquier, Johannes Muhle-Karbe, Joseph Mulligan, In-Sample and Out-of-Sample Sharpe Ratios for Linear Predictive Models, 2025, arXiv:2501.03938

Avoiding Overfitting: Searching for Parameter Plateau

To mitigate the risk of overfitting, system developers often employ techniques such as cross-validation and out-of-sample testing to ensure that their strategies remain robust across various market conditions and time periods.

Another technique to prevent overfitting involves selecting a parameter region, often referred to as a “plateau,” where the trading system maintains stable performance. Reference [2] introduced a method for quantifying this plateau and utilized particle-swarm optimization to search for it.

Findings

-The study highlights that quantitative trading performance depends heavily on parameter selection and is vulnerable to overfitting.

-It introduces the concept of a parameter plateau to identify stable and robust parameter regions rather than single optimal points.

-A plateau score algorithm is developed to replace the conventional approach of selecting the best in-sample parameters.

-The results show that parameters with high plateau scores exhibit more stable and consistent out-of-sample performance.

-The approach helps avoid “parameter islands” that perform well in-sample but fail out-of-sample.

-To improve search efficiency, the study applies particle swarm optimization instead of brute-force methods.

-Particle swarm optimization enables faster exploration of high-dimensional parameter spaces.

-Experiments demonstrate that the combined plateau and optimization approach improves both robustness and profitability.

-The method remains effective as strategy complexity increases from low- to high-dimensional parameter settings.

-The study also proposes suitable hyperparameter ranges for particle swarm optimization in this framework.

In short, the extent of plateau stability is quantified, and an efficient optimization algorithm is utilized to search for it. The out-of-sample test results show promise.

Reference

[2] Jimmy Ming-Tai Wu, Wen-Yu Lin, Ko-Wei Huang, Mu-En Wu, On the design of searching algorithm for parameter plateau in quantitative trading strategies using particle swarm optimization, Knowledge-Based Systems, Volume 293, 7 June 2024, 111630

Closing Thoughts

Taken together, these studies highlight that both model design and parameter selection are key sources of fragility in quantitative strategies. Overfitting arises not only from using too many weak signals but also from selecting unstable parameter configurations that fail to generalize out-of-sample. Approaches such as reducing model complexity, increasing data, and focusing on stable parameter regions through the concept of parameter plateaus offer practical ways to improve robustness. Overall, the evidence suggests that consistent performance depends less on optimizing in-sample results and more on ensuring stability across regimes and datasets.