Dynamic Correlations Between Bitcoin and the NASDAQ-100 Index

As cryptocurrencies, particularly Bitcoin (BTC), become more mainstream, investors have noticed an increasing correlation between BTC and the stock market. Some investors even argue that BTC now functions as a substitute risk asset for the technology sector.

Reference [1] presents a quantitative study on the correlation between BTC and the NASDAQ-100 (NDX) index, the causal relationships between them, and the influence of market sentiment on this relationship. Specifically, the study first employs univariate GARCH(1,1) models to capture volatility persistence in BTC and NDX returns. Second, it applies the DCC-GARCH model to measure time-varying correlations. Finally, it examines the influence of investor sentiment through regression and dynamic correlation analysis based on VIX levels.

The author pointed out,

This study aimed to quantitatively assess volatility spillovers, dynamic conditional correlations, and the moderating role of investor sentiment between Bitcoin (BTC) and the Nasdaq-100 index (NDX). The research specifically examined whether Bitcoin functions as a diversification asset and how market fear, indicated by the V IX, influences the correlation dynamics between BTC and NDX.

The key findings can be summarized as follows. First, both BTC and NDX exhibited significant volatility persistence, with BTC showing higher volatility magnitude and longer persistence (aBTC + [iBTC = 0.9322, (INDX + [iNDX = 0.9839). Second, the dynamic conditional correlation (DCC) between BTC and NDX was found to be varying over time and was significantly intensified during systematic stress events, such as the COVID-19 crisis and periods of monetary tightening. Third, the evidence suggested a weak yet significant bidirectional volatility spillover, particularly indicating that BTC volatility notably influenced NDX volatility during market stress periods. Fourth, investor sentiment (VIX) was identified as a strong moderator, with the regression results (y = 0.0106, p < 0.001) clearly showing that increases in market fear significantly amplified the correlation between BTC and NDX.

In short, the article concluded that,

• Both BTC and NDX showed strong volatility persistence, with BTC exhibiting higher volatility and longer persistence.
• The conditional correlation between BTC and NDX varied over time and intensified during market stress events such as the COVID-19 crisis and monetary tightening periods.
• A weak but significant bidirectional volatility spillover existed, with BTC volatility notably influencing NDX volatility during stress periods.
• Investor sentiment, measured by the VIX, acted as a strong moderator—rising market fear significantly increased the correlation between BTC and NDX.

This paper provides empirical evidence supporting investors’ observations and offers insights that can be integrated into trading and portfolio management frameworks.

Let us know what you think in the comments below or in the discussion forum.

References

[1] Boyu Zhang, From Diversifier to Amplifier? Investigating the BTC—NDX Linkage and the Modulating Role of VIX, Dean&Francis, 2025

Originally Published Here: Dynamic Correlations Between Bitcoin and the NASDAQ-100 Index

source https://harbourfronts.com/dynamic-correlations-bitcoin-nasdaq/

Market Timing Through Volatility Clustering and Causal Structure Identification

Volatility plays a crucial role in trading and risk management. These days, more portfolio managers are aware of and utilize volatility measures, even if they do not trade options. For example, we have previously discussed volatility-managed portfolios, where asset volatilities are used to size positions.

Reference [1] contributes to this body of research by classifying stocks according to their volatilities and then trading them. Specifically, the authors first employ the Gaussian Mixture Model (GMM) to group stocks with similar volatility characteristics. They then apply a causal inference framework based on the Granger Causality Test (GCT) and augmented with Effective Transfer Entropy (ETE) to identify lead-lag relationships, ultimately trading based on market timing signals generated by the lead stock.

The article pointed out,

This paper has put forward a novel methodology for volatility-driven statistical arbitrage in the context of stock market forecasting, which integrates sophisticated statistical techniques with machine learning models. By employing the GMM clustering algorithm to classify stocks according to mid-range volatility, we have demonstrated the potential of such clusters to act as indicators for predicting price movements. This method, combined with a robust causality analysis framework involving Granger Causality Tests, Peter-Clarke Momentary Conditional Independence, and Effective Transfer Entropy, identifies significant predictive relationships between stocks. Furthermore, the integration of DTW and KNN enhances predictive accuracy by aligning and classifying time series data, thereby enabling the anticipation of profitable trading opportunities.

The effectiveness of this integrated approach is demonstrated by the backtesting results. The trading strategies based on identified volatility clusters and causal relationships consistently outperformed the Buy & Hold benchmark across multiple performance metrics, including total returns, Sharpe Ratio, and maximum drawdown. Notably, the volatility-driven strategy yielded substantial returns with controlled risk exposure, as evidenced by the superior Sortino and Calmar ratios in comparison to conventional strategies.

In short, by using GMM to cluster stocks with comparable volatility characteristics and applying causal inference techniques to determine lead-lag pairs, the authors developed a trading strategy that achieved superior risk-adjusted returns.

This is an interesting development. However, we note two limitations:

• The framework involves multiple models, which increases the number of parameters and the risk of overfitting, and
• It appears that only in-sample tests were conducted.

Despite these limitations, there are valuable insights to be gained from this approach.

Let us know what you think in the comments below or in the discussion forum.

References

[1] Ivan Letteri, Statistical Arbitrage Volatility-Driven with Statistics and Machine Learning Models for Stock Market Forecasting, SN COMPUT. SCI. 6, 918 (2025).

Article Source Here: Market Timing Through Volatility Clustering and Causal Structure Identification

source https://harbourfronts.com/market-timing-volatility-clustering-causal-structure-identification/

Tail Risk Hedging and Trend Following: A Combined Framework

Investing in equities offers strong growth potential, but a key drawback is exposure to periodic drawdowns, which many investors find psychologically difficult to endure. To address this, some have proposed tail risk hedging strategies. However, portfolio managers are often reluctant to adopt them due to high carry costs, and researchers continue to debate their effectiveness.

Reference [1] implemented a particular tail risk hedging strategy and overlaid it on a trend-following approach, referred to as the Portable Alpha Portfolio.

The Portable Alpha Portfolio consists of two components: 100% exposure to the MSCI ACWI Index as the beta source, while alpha is generated through a tail risk hedging overlay and a 50% exposure to a trend-following strategy.

• The tail hedge is constructed by systematically purchasing three tranches of 10-delta SPX put options with one year to expiration, rolled quarterly, and notionally sized.
• The trend-following component includes 79 futures contracts, with normalized returns computed over four lookback periods: 3, 6, 9, and 12 months. Positions are taken long when the lookback return is positive and short otherwise.

The authors pointed out,

This study examines the performance enhancements from applying a Portable Alpha framework to a global equity portfolio by overlaying both trend-following and tail risk hedging strategies. The Portable Alpha portfolio maintains 100% exposure to the MSCI ACWI Index as its beta source, while alpha is introduced through a tail risk hedging overlay and a 50% exposure to a trend-following strategy…

The resulting Portable Alpha portfolio generated a large, positive, and statistically significant alpha of 0.25% per month after controlling for traditional equity factors, global government bond, and commodity returns. Absolute outperformance was concentrated during periods of crisis, particularly in the first half of the sample, with more recent periods showing broadly comparable returns to ACWI. However, the Portable Alpha portfolio consistently delivered superior risk-adjusted performance across the full sample, with notable improvements in downside protection. These findings are consistent with those in Schwalbach and Auret (2023). Performance attribution confirms that the Portable Alpha portfolio effectively captured ACWI excess returns, demonstrating that convex return streams can be overlaid to enhance performance without diluting core equity exposure.

In summary, this study finds that combining tail risk hedging with trend following adds value to a long-only equity portfolio, supporting the case for incorporating tail risk hedging into portfolio management.

Let us know what you think in the comments below or in the discussion forum.

References

[1] Bruno Schwalbach & Christo Auret, Enhancing global equity returns with trend-following and tail risk hedging overlays, Investment Analysts Journal, 2025

Post Source Here: Tail Risk Hedging and Trend Following: A Combined Framework

source https://harbourfronts.com/tail-risk-hedging-and-trend-following-a-combined-framework/

The Role of Investor Attention Index in Explaining Bitcoin Volatility

Modeling and forecasting volatility is essential in trading and risk management. Extensive research has been conducted on volatility modeling in traditional financial markets, and recently, attention has increasingly been directed toward cryptocurrency volatility. The standard approach often relies on econometric models.

Reference [1] applied the GARCH-MIDAS model to study Bitcoin volatility. However, unlike traditional approaches, it introduced two new types of explanatory variables:

• The first is investor attention, measured through Google Trends, social media activity, and news coverage, which reflects market participants’ interest and captures short-term market dynamics in speculative environments.
• The second is uncertainty indices, such as GEPU and GPR, which represent broader macroeconomic and geopolitical risks influencing market stability over longer horizons.

The authors pointed out,

This study highlights the significant role of investor attention and uncertainty indices in modelling Bitcoin volatility using the GARCH-MIDAS framework. Although uncertainty indices are more commonly applied in cryptocurrency volatility analysis, our findings demonstrate that attention indices, such as GTCA, outperform uncertainty indices like GEPU, GPR, and WUI in both explanatory power and forecasting performance. Notably, GTCA is easier to construct and, when developed comprehensively, provides superior insights into Bitcoin volatility dynamics.

Furthermore, an extended analysis of Ethereum, XRP, and BNB (Table 12) confirms that GTCA’s predictive power extends to other major cryptocurrencies, albeit with lower volatility levels compared to Bitcoin.

The two-variable models combining GTCA with GEPU, GPR, or WUI were identified as the most explanatory based on in-sample data and the best-performing according to out-of-sample results. These findings underscore the benefits of integrating GTCA with general uncertainty indices, as the complementary information they provide enhances the accuracy and reliability of Bitcoin volatility predictions.

This study contributes to the literature by being the first to integrate investor attention and uncertainty indices within a unified model for Bitcoin volatility. The construction of the GTCA index using a comprehensive set of search terms ensures robustness and distinguishes this work from prior studies. Additionally, by evaluating both in-sample and out-of-sample performance, this research addresses a critical gap in cryptocurrency volatility forecasting.

In short, the study found that the Google Trends Cryptocurrency Attention (GTCA) index is a significant driver of Bitcoin volatility and successfully integrated it, along with other uncertainty measures, into an effective econometric framework.

Let us know what you think in the comments below or in the discussion forum.

References

[1] Serkan Aras, Mehmet Ozan Ozdemir, Cihan Çılgın, Uncertainty or investor attention: Which has more impact on Bitcoin volatility?, Research in International Business and Finance 77 (2025) 103002

Article Source Here: The Role of Investor Attention Index in Explaining Bitcoin Volatility

source https://harbourfronts.com/the-role-of-investor-attention-index-in-explaining-bitcoin-volatility/

Impact of Artificial Intelligence on Financial Markets: a Quantitative and Qualitative Analysis

Artificial intelligence (AI) has become an integral part of modern finance, transforming how institutions analyze data, manage risk, and execute trades. By leveraging machine learning algorithms and natural language processing, AI systems can identify complex patterns in large financial datasets, forecast market movements, and detect anomalies that might signal fraud or structural inefficiencies.

As financial data grows in both volume and complexity, AI enables more adaptive, data-driven approaches, bridging the gap between quantitative modeling and real-time decision processes. Consequently, AI has a measurable impact on the market. Reference [1] examined the impact of AI on trading and risk management, performing both quantitative and qualitative analyses. The author pointed out,

As we have previously discussed, the core footprint of algorithmic trading and the entire spectrum of the financial markets, in one way or another, has been influenced by Artificial Intelligence (AI) technology. AI has profoundly changed the efficiency of the market, the execution of trading orders and the accuracy of trading decisions during the real-time analysis of available data, which has improved to an unprecedented level. Due to the advances in technology like AI, liquidity and the overall operations of the market have vastly improved because unlike humans, AI systems are able to outperform in trade execution speed and precision (Agarwal et al., 2021). AI also improves the accuracy of prediction that assists traders and investors in strategising and managing risks more effectively. Nevertheless, the integration of AI systems within trading structures has some consequences. Even if the implementation of AI technology comes with a lot of advantages, the stability of the market adds a new layer of risk. Arguments regarding flash crashes, categorised as a sudden drastic price decline due to an algorithm blunder, and systemic risk—the collapse of one AI system triggering an avalanche effect within a network of interlinked AI systems—pose a concern (Agarwal et al., 2021).

In short, AI has an overall positive impact on the market, particularly from the perspectives of execution and liquidity. However, it can also increase risks, as evidenced by the higher volatility associated with AI.

Let us know what you think in the comments below or in the discussion forum.

References

[1] Neeraj Kahol Sharma, Assessing the AI Impact on Financial Markets through Algorithmic Trading, Journal of Basic Science and Engineering, Vol. 22, No. 1, (2025)

Originally Published Here: Impact of Artificial Intelligence on Financial Markets: a Quantitative and Qualitative Analysis

source https://harbourfronts.com/impact-artificial-intelligence-financial-markets-quantitative-qualitative-analysis/

Return and Variance Risk Premia in the Bitcoin Market

The volatility risk premium (VRP) has been studied extensively in the literature, especially in equities. However, little work has been done in the crypto space. Reference [1] fills this gap by investigating the Bitcoin return premium (BP) and the Bitcoin variance risk premium (BVRP).

The authors utilized Bitcoin options data traded on Deribit from July 2017 to December 2022 to calculate the BVRP. The implied variance is computed using the same methodology as the VIX index. Additionally, they derived risk-neutral densities (RNDs) from the option volatility surface and subsequently used RNDs to classify Bitcoin market states as high volatility or low volatility.

The authors pointed out,

The BP is significantly higher than that of traditional investment assets such as currencies, commodities, and stocks, averaging around 66% per year….The annualized risk-neutral and physical monthly variances, proxied by the squared Bitcoin Volatility Index (BVIX) and the realized variance (BRV), are significantly high: 0.72 and 0.58, respectively. The corresponding variance risk premium is 0.14, much higher than that of the S&P 500 Index—approximately 2%, according to Bollerslev, Tauchen, and Zhou (2009).

We further analyze conditional estimates across market regimes. Our results indicate that BP is higher in the HV regime... The overall increased volatility leads to higher option price premia on average across all moneyness levels. The variance under the two probability measures is quite different and introduces a substantial VRP in both market regimes. Surprisingly, the low volatility cluster is characterized by a higher VRP of 0.17 compared to the high volatility cluster of 0.12, suggesting a potential disconnect between variance and VRP.  By relying on the average values of the premia within each cluster, we observe a negative relationship between the BP and BVRP in the Bitcoin market. This contrasts with the findings in S&P 500 Index market, where a positive relationship between variance risk premium and future returns has been reported by Bollerslev, Tauchen, and Zhou (2009) in a regression setup. Simultaneously, our clustering results indicate a positive relationship between returns and variance, supporting the inverse leverage effect in the Bitcoin market documented by Hou et al. (2020).

In short, the paper found that Bitcoin is far more volatile and exhibits a higher variance risk premium than the S&P 500, and that the Bitcoin return premium (BP) is also elevated. Risk premia vary over time as a function of two distinct volatility regimes.

This is an important contribution to the understanding of the crypto options market. However, the dataset extends only through 2022. Since then, Bitcoin has reached a broader user base, and its volatility dynamics have evolved. It would be interesting to examine whether the findings hold in the current market.

Let us know what you think in the comments below or in the discussion forum.

References

[1] Caio Almeida, Maria Grith, Ratmir Miftachov, Zijin Wang, Risk Premia in the Bitcoin Market, arXiv:2410.15195

Originally Published Here: Return and Variance Risk Premia in the Bitcoin Market

source https://harbourfronts.com/return-variance-risk-premia-bitcoin-market/