Abstract The paper analyzes the cryptocurrency ecosystem at both the aggregate and individual levels to understand the factors that impact future volatility. The study uses high-frequency panel data from 2020 to 2022 to examine the relationship between several market volatility drivers, such as daily leverage, signed volatility and jumps. Several known autoregressive model specifications are estimated over different market regimes, and results are compared to equity data as a reference benchmark of a more mature asset class. The panel estimations show that the positive market returns at the high-frequency level increase price volatility, contrary to what is expected from the classical financial literature. We attributed this effect to the price dynamics over the last year of the dataset (2022) by repeating the estimation on different time spans. Moreover, the positive signed volatility and negative daily leverage positively impact the cryptocurrenciesâ future volatility, unlike what emerges from the same study on a cross-section of stocks. This result signals a structural difference in a nascent cryptocurrency market that has to mature yet. Further individual-level analysis confirms the findings of the panel analysis and highlights that these effects are statistically significant and commonly shared among many components in the selected universe.
Anomaly detection is critical in the financial sector, especially as financial environments evolve with increasing digitization, posing challenges for real -time anomaly detection. Recently, deep learning (DL) algorithms have emerged as promising solutions for this problem. This study presents a DL -based anomaly detection model utilizing various algorithms, including LSTM, GRU, and 1dCNN, applied to Tesla's stock market and Ethereum cryptocurrency data sets. Hyperparameter optimization is performed using grid search. Results show that the GRU algorithm achieves the highest prediction score in both datasets, while the 1dCNN algorithm performs the lowest. Additionally, anomaly values are graphically demonstrated using GRU for both datasets. Accurate bookkeeping is essential for legitimate business operations, yet the complexity of financial auditing requires new solutions. Supervised and unsupervised machine learning techniques are increasingly applied to detect fraud and anomalies in accounting data. This paper addresses the challenge of detecting financial misstatements in general ledger (GL) data, proposing seven supervised ML techniques, including deep learning, and two unsupervised ML techniques. Models are trained and evaluated on real -life GL datasets, demonstrating high potential in detecting predefined anomaly types and efficiently sampling data. Practical implications of these solutions in accounting and auditing contexts are discussed. The rapid development of computer networks brings both convenience and security challenges due to various abnormal flows. Traditional detection systems, like intrusion detection systems (IDS), have limitations, necessitating real -time updates to function effectively. With the advent of machine learning and data mining, new methods for abnormal network flow detection have emerged. This paper introduces the random forest algorithm for detecting abnormal samples, proposing the concept of an abnormal point scale to measure sample abnormality based on similarity. Simulation experiments demonstrate the superiority of random forest -based detection in terms of model accuracy and computing efficiency compared to other methods.
Abstract This study examines the market efficiency in the prices and volumes of transactions of 41 cryptocurrencies. Specifically, the correlation dimension (CD), Lyapunov Exponent (LE), and approximate entropy (AE) were estimated before and during the COVID-19 pandemic. Then, we applied Studentâs t -test and F -test to check whether the estimated nonlinear features differ across periods. The empirical results show that (i) the COVID-19 pandemic has not affected the means of CD, LE, and AE in prices, (ii) the variances of CD, LE, and AE estimated from prices are different across pre-pandemic and during pandemic periods, and specifically (iii) the variance of CD decreased during the pandemic; however, the variance of LE and the variance of AE increased during the pandemic period. Furthermore, the pandemic has not affected all three features estimated from the volume series. Our findings suggest that investing in cryptocurrencies is advantageous during a pandemic because their prices become more regular and stable, and the latter has not affected the volume of transactions.
Abbas M. Ali, Abdullah Shah, Azaz Hassan Khan, Malik Umar Sharif · 8 authors
Software-based technical indicators have been widely used for the stock market forecasting, aiming to predict market direction. Even though many algorithms for the software based technical indicators are presented, there are almost no hardware implementations reported in the literature. In this paper, the hardware implementation is presented for three commonly used technical indicators: Moving Average Convergence/Divergence (MACD), Relative Strength Index (RSI), and Aroon. Latency evaluation is conducted for Bitcoin and Ethereum within a single-day timeframe, utilizing the Xilinx Zynq-7000 programmable SoC XC7Z020-CLG484-1 platform. Additionally, various hardware/software (HW/SW) partitioning strategies are explored to leverage the flexibility of software alongside the performance advantages of hardware via the Zynq SoC platform. The results show that the best performing technical indicator is MACD with a speedup of 30 times over its software only counterpart. Furthermore, a hybrid design integrating multiple technical indicators is proposed, pairing MACD with RSI due to their competitive throughput values, differing by only 0.38 microseconds. This hybrid approach capitalizes on the parallel processing capabilities of hardware, enabling multiple systems to operate simultaneously.
Cryptocurrencies have become an attractive asset class for all types of investors. A relevant question is whether their inclusion in portfolios improves their risk-return output. In this chapter, we conduct an empirical study of the effect of the inclusion of Bitcoin and Ethereum in the portfolio of a European investor. Additionally, we analyze the results of previous studies on this question under other assumptions. The empirical data are overwhelming regarding the attractiveness of Bitcoin and by extension other cryptocurrencies as an asset class. The important question is whether this appeal is temporary and will eventually disappear so investors do not have to worry about this new asset class. In the chapter we discuss this issue.
We study how trading fees and continuous-time arbitrage affect the profitability of liquidity providers (LPs) in Geometric Mean Market Makers (G3Ms). We use stochastic reflected diffusion processes to analyze the dynamics of a G3M model under the arbitrage-driven market [Milionis et al. 2022a. âAutomated Market Making and Loss-Versus-Rebalancing.â arXiv e-prints]. Our research focuses on calculating LP wealth and extends the findings of Tassy and White [Tassy and White. 2020. âGrowth Rate of a Liquidity Provider's Wealth in xy = c Automated Market Makers.â] for the constant product market maker (Uniswap v2) to a broader range of G3Ms, including Balancer. This allows us to calculate the long-term expected logarithmic growth of LP wealth, offering new insights into the complex dynamics of AMMs and their implications for LPs in decentralized finance.
Using daily returns on large-cap altcoins, this paper uses power-law functions to model cryptocurrency-specific exposure to events exhibiting potentially large standard deviations. Since our analysis provides evidence for power-law behavior in the returns on cryptocurrencies, co-fractality analysis is employed to explore potential co-dependencies in the heavy-tailed part of return distributions. The findings indicate that the potential arrival of events exhibiting large standard deviations in Bitcoin returns can hardly be diversified using other sample altcoins. Other altcoins exhibit very similar features in terms of co-dependencies. Further results show that co-fractal behavior is not specific to any subsample.
This paper investigates portfolio optimization methodologies and short-term investment strategies in the context of the cryptocurrency market, focusing on ten major cryptocurrencies from June 2020 to March 2024. Using hourly data, we apply the Kurtosis Minimization methodology, along with other optimization strategies, to construct and assess portfolios across various rebalancing frequencies. Our empirical analysis reveals significant volatility, skewness, and kurtosis in cryptocurrencies, highlighting the need for sophisticated portfolio management techniques. We discover that the Kurtosis Minimization methodology consistently outperforms other optimization strategies, especially in shorter-term investment horizons, delivering optimal returns to investors. Additionally, our findings emphasize the importance of dynamic portfolio management, stressing the necessity of regular rebalancing in the volatile cryptocurrency market. Overall, this study offers valuable insights into optimizing cryptocurrency portfolios, providing practical guidance for investors and portfolio managers navigating this rapidly evolving market landscape.
Richard Harris, Murat MazibaĆ, Dooruj Rambaccussing
Cryptocurrencies are characterized by high volatility and low correlations with traditional asset classes, and present an intriguing investment opportunity. However, their inherent risks and regulatory uncertainties make direct investment challenging for many investors. This paper addresses this challenge by proposing a replication framework that employs machine learning to create synthetic portfolios that replicate the risk-adjusted return profile and diversification benefits of Bitcoin, by far the largest cryptocurrency by market share. We show that the synthetic portfolios offer a compelling alternative to direct investment in Bitcoin, delivering superior risk-adjusted returns net of trading costs while mitigating the risks that are associated with holding Bitcoin directly. Furthermore, the synthetic portfolios provide better diversification benefits and lower tail risk.
Erdinç Akyıldırım, Ahmet Faruk Aysan, OÄuzhan Ăepni, Ăzge Serbest
This paper explores the relationship between news media sentiment and spillover effects in the cryptocurrency market. By employing a time-varying parameter vector autoregressive model, we initially develop measures of spillover specific to individual cryptocurrencies. Subsequently, we employ unique data on cryptocurrency-specific sentiment to assess its impact on these spillover measures using panel fixed effects regression analysis. Our findings indicate that news media sentiment plays a significant role in explaining the spillover dynamics within the cryptocurrency market. Unlike traditional assets, it appears that only positive sentiment affects the spillovers among cryptocurrencies, suggesting an asymmetric effect. Taking into account various characteristics of cryptocurrencies, we find that sentiment's impact on spillover is more pronounced in community-based coins than in those driven by firms. An examination of news content suggests that sentiment pertaining to emotional and risk aspects of cryptocurrencies predominantly influences these spillovers. Additionally, a comparative analysis of sentiment derived from social media and traditional news sources reveals a stronger influence of the former on spillover effects. Through extensive robustness checks, our research consistently affirms the pivotal role of sentiment in driving spillovers among cryptocurrency returns, underlining the importance of sentiment analysis in understanding the dynamics of the cryptocurrency market.
This research aims to empirically investigate the portfolio risk associated with crypto assets. In other words, we want to investigate whether the inclusion of crypto assets in a portfolio can minimize the portfolio risk or not, because it is argued that there is a lower degree of correlation between crypto assets and traditional assets. In order to achieve our research objectives, we employ the Vector Autoregressive Model (VAR) by using five different asset classes. The first two variables are taken from the crypto assets, Bitcoin and Ethereum, and the remaining three variables for Gold, Crude Oil and VIX (Chicago Board Options Exchange's (CBOE) volatility index). Our research strategy will be based on an analysis for unit root, optimal lag selection, coefficient matrix, checking VAR stability, the Granger causality test, and impulse response function (IRF). Our findings suggest that none of the indicators of traditional assets drive and explain Bitcoin. We also found that only Bitcoin is significantly related to Ethereum. while none of the other variables are statistically useful to explain the variation in the Ethereum. Based on these findings it can be recommended that the inclusion of crypto assets into a portfolio reduces risk because none of the indicators of crypto assets are significantly related to the indicators of traditional assets.
In the dynamic world of finance, the application of Artificial Intelligence (AI) in pair trading strategies is gaining significant interest among scholars. Current AI research largely concentrates on regression analyses of prices or spreads between paired assets for formulating trading strategies. However, AI models typically exhibit less precision in regression tasks compared to classification tasks, presenting a challenge in refining the accuracy of pair trading strategies. In pursuit of high-performance labels to elevate the precision of classification models, this study advanced the Triple Barrier Labeling Method for enhanced compatibility with pair trading strategies. This refinement enables the creation of diverse label sets, each tailored to distinct barrier configurations. Focusing on achieving maximal profit or minimizing the Maximum Drawdown (MDD), Genetic Algorithms (GAs) were employed for the optimization of these labels. After optimization, the labels were classified into two distinct types: High Risk and High Profit (HRHP) and Low Risk and Low Profit (LRLP). These labels then serve as the foundation for training machine learning models, which are designed to predict future trading activities in the cryptocurrency market. Our approach, employing cryptocurrency price data from 9 November 2017 to 31 August 2022 for training and 1 September 2022 to 1 December 2023 for testing, demonstrates a substantial improvement over traditional pair trading strategies. In particular, models trained with HRHP signals realized a 51.42% surge in profitability, while those trained with LRLP signals significantly mitigated risk, marked by a 73.24% reduction in the MDD. This innovative method marks a significant advancement in cryptocurrency pair trading strategies, offering traders a powerful and refined tool for optimizing their trading decisions.
Portfolio optimization is the art and science of constructing investment portfolios to strike a balance between risk and return. Traditional models, like Modern Portfolio Theory (MPT) and the Capital Asset Pricing Model (CAPM), have long served as the foundation for portfolio management. However, these methods often struggle to account for the intricacies of real financial markets. This study explores cutting-edge portfolio optimization techniques, incorporating unconventional assets such as cryptocurrencies and ESG investments to bolster diversification. Leveraging machine learning and artificial intelligence, we aim to improve asset selection, risk assessment, and allocation, accommodating the dynamic and non-linear nature of markets. Furthermore, we evaluate how these models perform in various market conditions through empirical analyses of historical data. Our findings indicate that adopting a more adaptable portfolio optimization framework can help investors navigate changing market dynamics more effectively, ultimately achieving a more efficient risk-return trade-off. These insights are invaluable for both individual and institutional investors, enabling them to construct portfolios that adapt to evolving market realities while optimizing wealth preservation and growth. In essence, this research contributes to the ongoing discourse on portfolio optimization, offering potential enhancements for investment strategies in today's financial landscape.
This research aims to examine the influence of cryptocurrencies on stock market prices in Indonesia. This research uses multiple regression analysis using daily tme series data from 2020-2022 so that the number of observations in this research is 1096. The findings in this research show mixed results between cryptocurrency assets and stock market prices in Indonesia. From the research results, Bitcoin does not have a significant influence on stock market prices in Indonesia, while Ethereum and Binance Coin have a positive and significant influence, but this is different from Maker and Pax Gold. Maker and Pax Gold have a negative and significant influence on stock market prices. The findings in this research show that the nature of the influence of cryptocurrency on stock market prices in Indonesia is not the same but depends on the cryptocurrency asset itself. The findings in this research suggest that investors and market players need to consider these two assets together in their investment strategies.
This paper investigates portfolio optimization methodologies and short-term investment strate-gies in the context of the cryptocurrency market, focusing on ten major cryptocurrencies from January 2020 to November 2023. We employ high frequency data and utilize the Kurtosis Mini-mization methodology, alongside other optimization strategies, to construct and evaluate port-folios under different rebalancing frequencies. The empirical analysis reveals that cryptocurren-cies exhibit significant volatility, skewness, and kurtosis, necessitating sophisticated portfolio management techniques. We find that the Kurtosis Minimization methodology consistently outperforms other optimization strategies, delivering optimal returns to investors, particularly in shorter-term investment horizons. We demonstrate the diversification benefits of integrating cryptocurrencies into multi-asset portfolios and emphasize the importance of regular portfolio rebalancing in the volatile cryptocurrency market. Our findings offer insights for portfolio man-agers and investors seeking to optimize their investment outcomes in the cryptocurrency market, highlighting the importance of risk management, diversification, and dynamic portfolio man-agement strategies.
In this paper, we describe and apply different models of portfolio construction in the selection between a small number of big-cap cryptocurrencies. Our purpose is to select the minimum riskiness between cryptocurrencies, comparing different risk measures and maximum diversification. We build our models without the constraints of the expected returns. Without relying on expected returns, we have the same condition on the comparison between them. Cryptocurrencies are not common stock or other assets indexed in the market but it is interesting to study how diversification can significantly improve investment performance. We first give the methodology to use high-frequency observation data, in the numeral approximation especially in the novel application of the Risk parity models, used with different risk measures we can achieve a very good result, from the position of gaining and variation. Since Risk parity models divide the weights of the asset in equal risk contribution proportion, it is suggested to use a small number of cryptocurrencies, otherwise their performance will be close to the uniform portfolio. To the traditional Mean Variance model, and the alternative, Expected shortfall/Conditional Value at Risk, we use three versions of Risk Parity with two different risk measures and a naive risk parity. The uniform portfolio is used as a benchmark for selection comparison with the other portfolio models. We give the conditions for the Risk Parity with the Expected shortfall/Conditional Value at Risk (CVaR) to guarantee convergence with the numerical approximation. In the end, we study the tradeoff between each model and which is more suitable for a small cryptocurrency portfolio.
The cryptocurrency market has been growing frantically in number of cryptocurrencies, online exchanges, and market capitalization, which has amplified the need for comprehensive and robust pricing models. Using a database of all eligible cryptocurrencies listed on the CoinMarketCap website, we study the relationship between returns and several potential pricing factors, such as size (market capitalization), momentum, liquidity, and maturity. The analysis was conducted from December 27, 2013, to December 29, 2020, using weekly data for 3'667 cryptocurrencies. Results point out that portfolios of cryptocurrencies with smaller market capitalization, higher reversal, lower liquidity, and lower maturity tend to offer higher returns. The 5-factor model that additionally includes illiquidity and maturity performs better than the 3-factor model previously proposed in the literature, meaning that illiquidity and maturity significantly help capture the cross-sectional cryptocurrency risk premia. The 5-factor model presented seems robust to different procedures to construct portfolios and factors.
We introduce a model that derives a metric to answer the question: what is the expected gain of a staker? We calculate the rewards as the staking return in a Proof-of-Stake (PoS) consensus context. For each period of block validation and by a forward approach, we prove that the interest is given by the ratio of the average staking gain to the total staked coins. Some additional PoS features are considered in the model, such as slash rate and Maximal Extractable Value (MEV), which marks the originality of this approach. In particular, we prove that slashing diminishes the rewards, reflecting the fact that the blockchain can consider stakers to potentially validate incorrectly. Regarding MEV, the approach we have sheds light on the relation between transaction fees and the average staking gain. We illustrate the developed model with Ethereum 2.0 and apply a similar process in a Proof-of-Work consensus context.
Abstract The main objective of this paper is to forecast the realized volatility (RV) of Bitcoin futures (BTCF) market. To serve our purpose, we propose an augmented heterogenous autoregressive (HAR) model to consider the information on time-varying jumps observed in BTCF returns. Specifically, we estimate the jump-induced volatility using the GARCH-jump process and then consider this information in the HAR model. Both the in-sample and out-of-sample analyses show that jumps offer added information which is not provided by the existing HAR models. In addition, a novel finding is that the jump-induced volatility offers incremental information relative to the Bitcoin implied volatility index. In sum, our results indicate that the HAR-RV process comprising the leverage effects and jump volatility would predict the RV more precisely compared to the standard HAR-type models. These findings have important implications to cryptocurrency investors.
We provide a novel perspective on the Bitcoin market, investigating determinants of investor positions and their response to public information proxied by sentiment indicators. We distinguish between investors by size and observe their respective behaviour concerning incoming information. We find that price dynamics and media coverage lead to different decisions depending on the Bitcoin portfolio size. Retail investors react strongly to incoming public information and media narratives, with their decisions strongly influenced by sentiment and media attention. Conversely, the response of large-scale investors to such information is much weaker because they arguably have different, non-public information and divergent investment objectives.
In this paper, we analyze traders' behavior within both centralized exchanges (CEXs) and decentralized exchanges (DEXs), focusing on the volatility of Bitcoin prices and the trading activity of investors engaged in perpetual future contracts. We categorize the architecture of perpetual future exchanges into three distinct models, each exhibiting unique patterns of trader behavior in relation to trading volume, open interest, liquidation, and leverage. Our detailed examination of DEXs, especially those utilizing the Virtual Automated Market Making (VAMM) Model, uncovers a differential impact of open interest on long versus short positions. In exchanges which operate under the Oracle Pricing Model, we find that traders primarily act as price takers, with their trading actions reflecting direct responses to price movements of the underlying assets. Furthermore, our research highlights a significant propensity among less informed traders to overreact to positive news, as demonstrated by an increase in long positions. This study contributes to the understanding of market dynamics in digital asset exchanges, offering insights into the behavioral finance for future innovation of decentralized finance.
Cryptocurrency investment approaches continue to evolve rapidly. Traditionally, cryptocurrency holders tend to actively support up to several distinct projects, focusing their selection criteria on specific project characteristics, project team and community, existing markets and liquidity levels, as well as the perception of each unique projectâs broadly understood âmission and visionâ and âfuture potential.â In this chapter, we will explore an index-based investment strategy as an alternative to the more traditional single- or oligo-asset approaches. In the index-based paradigm, multi-asset strategy involves equalization and redistribution of risk exposure across multiple, pre-vetted portfolio positions. This strategy, novel to the cryptocurrency space, also involves risk reduction through cost averaging, dilution of cyber security-related risk(s), as well as mitigation of liquidity restrictions related to individual-position market liquidity characteristics. Additional discussion of software platforms, including both custodial and non-custodial wallets, and the associated risk-benefit considerations, will also be included in this manuscript.
This article investigates the Ethereum Merge, which occurred on 15 September 2022, and we employ the time-series difference in differences (DiD) model and vector autoregression (VAR) models and analyse how the protocol change from proof-of-work to proof-of-stake (PoS) affects the dynamic relationship between cryptocurrency returns and network factors. The results show that the Merge caused a structural change between Ethereum and Bitcoin networks. The network factors of Ethereum show a significant increase compared to Bitcoin, the cointegration has been strengthened and the lag length is shortened after the Merge. The spillover effect on the Bitcoin network can be seen from both DiD and VAR, indicating the increasing impact of the Ethereum network on Bitcoin. The concern of losing the number of participants due to the implantation of PoS on cryptocurrency is not apparent on Ethereum Merge, and it increases the investorsâ attention and involvement.
Salman Bahoo, Marco Cucculelli, Xhoana Goga, Jasmine Mondolo
Abstract Over the past two decades, artificial intelligence (AI) has experienced rapid development and is being used in a wide range of sectors and activities, including finance. In the meantime, a growing and heterogeneous strand of literature has explored the use of AI in finance. The aim of this study is to provide a comprehensive overview of the existing research on this topic and to identify which research directions need further investigation. Accordingly, using the tools of bibliometric analysis and content analysis, we examined a large number of articles published between 1992 and March 2021. We find that the literature on this topic has expanded considerably since the beginning of the XXI century, covering a variety of countries and different AI applications in finance, amongst which Predictive/forecasting systems, Classification/detection/early warning systems and Big data Analytics/Data mining /Text mining stand out. Furthermore, we show that the selected articles fall into ten main research streams, in which AI is applied to the stock market, trading models, volatility forecasting, portfolio management, performance, risk and default evaluation, cryptocurrencies, derivatives, credit risk in banks, investor sentiment analysis and foreign exchange management, respectively. Future research should seek to address the partially unanswered research questions and improve our understanding of the impact of recent disruptive technological developments on finance.