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.
The media, speculators, investors, and governments throughout the world have all become increasingly interested in cryptocurrencies in recent years. The price swings of cryptocurrencies are notoriously unstable and have a high level of volatility. This study focused on modeling that volatility of cryptocurrencies, the purpose of this study is to identify the most suitable or appropriate innovation distribution and different GARCH Models to model the returns of the most popular cryptocurrencies. The majority of our work was focused on the top ten cryptocurrencies, but we also extended our analysis to 377 cryptocurrencies. To describe the time dependent volatility of the cryptos, we utilize eleven different GARCH models, including the sGARCH, iGARCH, GJRGARCH, eGARCH, tGARCH, AVGARCH, CSGARCH, ALLGARCH, NGARCH, APARCH, and NAGARCH. For the research period of September 14, 2014 to November 10, 2022, the daily closing prices of cryptocurrencies are collected. The underlying innovation(error) distribution are assumed to be from one of the following eight distributions of Normal, Studentâs t, Generalized Error, Skew Normal, Skew Studentâs t, Skew Generalized error, Normal Inverse Gaussian and Generalized Hyperbolic Distribution. Each GARCH-type model was fitted with this eight innovations.
The aim of this paper is to examine the relationship between uncertainty indices (Geopolitical Uncertainty Index and Global Economic Policy Uncertainty Index) and cryptocurrencies. This study evaluated the behavior of cryptocurrencies with the evolution of uncertainties (GPU, EPU) on returns and volatility in terms of safe heaven as in traditional specualtive assets it increases their volaitility and reduces risk. For this purpose, this study examines the relationship between uncertanities indices, gold returns and crptocurrency by using the OLS regression for the monthly data from April 2017 to April 2022. The findings of this study indicate that the return and volatility of cryptocurrency increases. In particular, we note that the cryptocurrency market could serve as a weak hedge and safe against GEPU during a bull market; It could be considered a strong hedge, but in most cases could not serve as a safety against GPR. However, in case of Gold it is found that it serves as weak hedge against uncertainity indices and is not considered as safe heaven against GEPU and GPR. This study expands the current research on uncertainity indices and provides unique insight about the speculative nature of cryptocurrencies and safe heaven.
Abstract Cryptocurrencies are in the center of attention of investors, public authorities and researchers, but the interest has shifted from purely financial aspects regarding the way of trading, lack of regulation and supervision of transactions, volatility, correlation with other assets to aspects related to sustainability taking in account the high energy consumption generated by the mining process and the impact on environmental pollution. Bitcoin was chosen for the research considering the dominance that this financial asset has on the cryptocurrency market and its position as alpha currency.The article focuses on the relationship between Bitcoin transactions and energy consumption, for period 1st January 2019â31st of May 2022, this interval having significant price movements. The authors made a prediction of the Bitcoin price using a complex meta-model and SQL analytical functions. The analysis is based on 15 fundamental variables in order to forecast the price: Bitcoin data (prices and volume), electricity price and traded quantity on day-ahead market (DAM), gas price and traded quantity on DAM, inflation in EU, EU-ETS emissions certificates and oil prices. The study reveals the importance of the relationship Bitcoinâenergyâcarbon emissions, elements that capture the impact of the mining process on the environment from the perspective of energy consumption. Investors on the Bitcoin market must be aware not only of the importance of financial aspects on the price of cryptocurrencies (inflation, demand, offer), but also of other elements related to the evolution of energy prices (electricity, oil, gas, renewable energy) and the evolution of emissions certificates prices. Considering the promotion of the principles of sustainable development on the capital market, portfolio investors have become increasingly attentive to the social and environmental performance of financial assets. This study aims to make financial market players aware of the non-financial implications of their transactions. In addition, the energy transition and the reconfiguration of the energy mix are elements of impact on the cryptocurrency market through the technical levers involved in the mining process.
Cryptocurrency price fluctuations are increasingly interesting and are of concern to researchers around the world. Many ways have been proposed to predict the next price, whether it will go up or down. This research shows how to create a patterned dataset from an API connection shared by Indonesia's leading digital currency market, Indodax. From the data on the movement of all cryptocurrencies, the lowest price variable is taken for 24 hours, the latest price, the highest price for 24 hours, and the time of price movement, which is then programmed into a pattern dataset. This patterned dataset is then mined and stored continuously on the MySQL Server DBMS on the hosting service. The patterned dataset is then separated per month, and the data per day is calculated. The minimum, maximum, and average functions are then applied to form a graph that displays paired lines of the movement of the patterned dataset in Crash and Moon conditions. From the observations, the Patterned Graphical Pair dataset using the Average function provides the best potential for predicting future cryptocurrency price fluctuations with the Bitcoin case study. The novelty of this research is the development of patterned datasets for predicting cryptocurrency fluctuations based on the influence of bitcoin price movements on all currencies in the cryptocurrency trading market. This research also proved the truth of hypotheses a and b related to the start and end of fluctuations.
This paper empirically estimates information asymmetry in cryptocurrency markets using the Probability of Informed Trading (PIN) and Adjusted PIN metrics . These markets, characterized by a high proportion of algorithmic trading and large volumes of high-frequency data, present a promising environment for analyzing informed trading behavior. We introduce a modified estimation procedure for Adjusted PIN, addressing floating-point errors and issues with local extrema, thereby improving its accuracy compared to the traditional naive approaches comÂmonly used in the literature. Additionally, we propose an alternative trade aggregation method at higher frequencies than the conventional daily aggregation to enhance the efficiency of both PIN and Adjusted PIN models. Through analysis of both simulated and real data, we demonstrate that aggregating total buy and sell trades on a daily basis results in less meaningful estimates due to noisy input data, making it difficult to capture informed trader activity. The true optimal trade aggregation frequency is still to be further investigated, as increasing the frequency introduces heterogeneity in order imbalances, and the specific frequencies at which informed traders operate are still unknown. Finally, several empirical studies are conducted to evaluate the behavior of the metrics, revealing that illiquid cryptocurrencies exhibit relatively higher estimated probabilities of informed trading. This finding aligns with similar results observed in equity markets.
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.
Abstract In this paper, we study the return and volatility connectedness between cryptocurrencies and DeFi Tokens, considering the impact of different uncertainty indices on their connectivity. Initially, we estimate a TVPâVAR model to obtain the total connectedness between the two markets. We find that returns on the cryptocurrencies transmit significantly larger shocks and, thus, are responsible for most variations in the majority of DeFis' returns. Then, to analyse the impact of uncertainty on total return and volatility connectedness, we use four factors, namely, Economic Policy Uncertainty (EPU), The Chicago Board Options Exchange Volatility Index (VIX), Infectious Disease Equity Market Volatility Tracker (IDâEMV) and Geopolitical Risks (GPR). We find that except for geopolitical risks, all three measures have a positive impact on return and volatility connectedness, while GPR exerts a negative impact. Finally, we provide implications for researchers, market participants and policymakers.
This study examines the interconnectedness between central bank digital currencies (CBDC) index, digital assets and financial stability. First, we use the CBDC index as a measure of financial stability and examine its connectedness with other known measures of financial stability used in the literature. Secondly, we analyse the connectedness of CBDC index with digital assets such as cryptocurrencies and non-fungible tokens and various measures of financial stability. By analysing index returns of CBDC data and applying various connectedness measures to CBDC index, cryptocurrencies, stablecoins and NFTs, we gain insights into the relationships among these assets within a framework. The findings reveal a significant level of connectedness between CBDCs index, digital assets and financial stability. Our analysis shows a weak positive connectedness between CBDCs index and digital assets, indicating that movements in the CBDC index are not closely related to the performance of various digital assets and have a very small contribution to the changes in the returns of digital assets. Furthermore, the study finds bidirectional connectedness between CBDCs and other financial stability measures, suggesting that changes in CBDC performance can influence the overall stability of the financial system, and vice versa. This highlights the importance of carefully considering the design and implementation of CBDCs to ensure they support financial stability objectives.
The research paper takes a deep dive into crypto currency market dynamics and regulation to bridge the gap of understanding these issues with implications for the economy. The arrival of crypto-currencies changes the terrain of finance completely by bringing in a new asset class with unprecedented level of volatility. Through this research paper, we will try to conduct a thorough investigation into the relationships within the crypto currency market, which will cover trend analysis, volatility patterns, and sketching the volatile regulatory status that accompanies this evolving environment. By adopting a holistic strategy including quantitative data analysis, qualitative research and regulatory watch, this paper will contribute to the knowledge about the mechanisms behind crypto currency markets and provide actionable strategies to the stakeholders enabling them to determine a clear course of action in this dynamic environment. The research is seeking to offer essential impressions about crypto currency ecosystem dynamics and regulatory pressure as a contribution to getting a bigger understanding of the sector which is emerging fast.
This paper explores whether the overall evolution of Bitcoin log-prices would manifest a log-period power-law singularity (LPPLS) signature, eventually resulting in the arrival of a finite-time singularity. Calibrating the LPPLS model using daily data on Bitcoin covering the 2011â2023 period, this study indeed finds evidence for a strong LPPLS signature suggesting the arrival of a spontaneous singularity in the year 2129. Further striking evidence suggests that Bitcoin will experience what we term a close-to-singularity-condition near to the year 2050âa remarkable coincidence with the recently documented arrival of a finite-time singularity in U.S. equities.
The main aim of the study will be to identify the major factors affecting the market price of crypto currencies and to analyze the nature of the crypto currency market from a global vs. Indian perspective. In India, crypto currency trading is not yet fully developed, and it has a history of being used to finance illicit operations from the start. Due to significant volatility and unlawful trading, India is considering bringing crypto currency trading under the jurisdiction of SEBI. Due to a high increase in interest in crypto currencies such as Bitcoin, there is a real concern about the ability of this currency to replace the monetary system by overcoming the issues related to it. Several aspects need to be considered to estimate the ability of replacement. The study will take into consideration five main cryptographic currencies. According to Coin MarketCap, the top five crypto currencies by market capitalization as of August 2023 are Bitcoin (BTC), Ethereum (ETH), Tether (USDT), Binance Coin (BNB), and Cardano (ADA).
Sonal Sahu, JosĂŠ Hugo Ochoa VĂĄzquez, Alejandro Fonseca RamĂrez, JongâMin Kim
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.