In this paper, I explore various machine-learning models for predicting high-frequency returns for four of the most popular cryptocurrency perpetual futures trading pairs: BTCUSDT, ETHUSDT, MATICUSDT, and SOLUSDT. Specifically, I train and evaluate models for classifying the direction of the smoothed mid-price change for high-frequency prediction horizons. I introduce a novel data set constructed from a live WebSocket stream from Binance, the world's largest centralized cryptocurrency exchange. I explore how different data representations affect model performance and how performance varies for different trading pairs and prediction horizons. I use a mixture of traditional machine learning and deep learning models and show that simple and explainable traditional models can rival the performance of far larger and more complex state-of-the-art deep learning models.
Muhammad Yousaf, Muhammad Imran Tariq, Abdul Jabbar, Syed Qaiser Jalil
This comprehensive review paper explores the diverse landscape of cryptocurrency forecasting, tracing its evolution from an alternative to traditional monetary systems to its significant growth in the global financial arena. It consolidates existing research by categorizing and analyzing 234 scholarly articles, organizing them into machine learning, deep learning, deep reinforcement learning, and statistical methodologies, and evaluating the related metrics. The case study titled “Examining the performance differences between backtesting and forward testing” highlights the challenges investors face, as strategies that appear effective in backtesting often fail in practical use. Another case study, “Social Data Exploration in Cryptocurrency Trends,” examines how social media data can provide insights into market movements and investor sentiment, revealing the impact of social trends on cryptocurrency prices. The findings section provides a detailed view, illuminating trends such as yearly publication rates, methodological distributions, input features, training/testing splits, the total number of data samples considered, and forecasting time horizons. This survey paper serves as a valuable resource, providing researchers and investors with a solid foundation for understanding and navigating the dynamic field of cryptocurrency forecasting.
This paper argues that cryptocurrency, including cryptocurrencies such as Bitcoin, should be understood as qualified property. We build up support for this claim in three stages: first, we outline the diversity of cryptocurrencies, a diversity which is underappreciated in the current literature. We then outline the importance of theoretical presuppositions which operate in the ‘cryptocurrencies as property’ debate. This is followed by a detailed critique of established positions. We explore the shortcomings of three commonly-held views in the debate: that cryptocurrencies are property, belonging to a third category of personal property beyond the choses in possession/choses in action distinction; that cryptocurrencies are property and belong to the category of choses in action; and, lastly, that cryptocurrencies are not property at all. We then develop a new analysis of property in cryptocurrencies, taking into account both the variety of cryptocurrencies which exist and capturing the doctrine operating currently in property law, including its theoretical underpinnings. Through understanding rights in property as relative, and property itself as a scale, we avoid the shortcomings of other popular accounts whose shortcomings we identify, and show that cryptocurrencies are a form of choses in possession – namely, qualified property.
Pohsun Feng, Ziqian Bi, Yan, Lawrence K. Q., Yizhu Wen · 17 authors
A detailed exploration of blockchain technology and its applications across various fields is provided, beginning with an introduction to cryptography fundamentals, including symmetric and asymmetric encryption, and their roles in ensuring security and trust within blockchain systems. The structure and mechanics of Bitcoin and Ethereum are then examined, covering topics such as proof-of-work, proof-of-stake, and smart contracts. Practical applications of blockchain in industries like decentralized finance (DeFi), supply chain management, and identity authentication are highlighted. The discussion also extends to consensus mechanisms and scalability challenges in blockchain, offering insights into emerging technologies like Layer 2 solutions and cross-chain interoperability. The current state of academic research on blockchain and its potential future developments are also addressed.
With the gradual development and integration of artificial intelligence into various industries, there is also a great range of integration in the financial industry. Therefore, this article focuses on the trend prediction model and financial risk management problems of deep reinforcement learning (DRL), one of the largest branches of artificial intelligence, in the cryptocurrency market. In addition, in the experimental part of this paper, the artificial intelligence machine learning Long short-term memory network (LSTM) model is used to make effective time series prediction and analysis on the relevant data of the cryptocurrency market, so as to make a large-scale analysis to improve the accuracy of market trend prediction and the effectiveness of risk management. In addition, in this experiment, technology-related indicators, emotional states of financial market customers and other content related to large language models are combined. While optimizing investment strategy by using deep reinforcement learning algorithm, machine learning prediction model is also used to capture the time dependence of financial market. The experimental results also show that the predicted results are consistent with the actual value. Therefore, the model has high practical application value in predicting the time series price trend of cryptocurrency in the financial market and indicates that the integrated DRL model framework can further optimize and manage the price and trading strategy of the financial market. Future research should focus on improving the LSTM model and incorporating more features to improve prediction accuracy and adapt to market changes.
The trinity of global warming, climate change, and air pollution casts an ominous shadow over society and the environment. At the heart of these threats lie carbon emissions, whose reduction has become paramount. Blockchain technology and the internet of things (IoT) emerge as innovative tools for establishing an efficient carbon credit exchange. This paper presents a blockchain and IoT-centric platform for carbon credit exchange, paving the way for transparent, secure, and effective trading. IoT devices play a pivotal role in monitoring and verifying carbon emissions, safeguarding the integrity and accountability of the trading process. Blockchain technology, with its decentralized and immutable nature, empowers the platform with transparency, reduced fraud, and enhanced accountability. This platform aims to arm organizations and individuals with the ability to actively curb carbon emissions, fostering collective efforts towards global pollution reduction goals.
Abstract The adoption of digital assets and distributed ledger technology in finance is rapidly increasing. This adoption introduces new types of risks, currently not adequately covered in conventional risk management frameworks. This paper identifies, reviews, and categorises these risks. It draws on a systematic review of literature and classifies the vulnerabilities by layer—network layer, consensus layer, protocol layer, and enablement layer.
This article attempts to challenge the argument that bitcoin cannot be owned within a libertarian legal order. According to the contested view, bitcoin, as a digital asset, does not meet the criteria for traditional ownership due to its nonphysical nature as an intangible asset. However, the counterargument presented in the article asserts that people should have property rights over bitcoin due to the facts that the technology behind bitcoin makes it a scarce rivalrous resource and conflicts over the use of bitcoin goods can arise. It is the general function of property rights to avoid possible clashes over the use of scarce, rivalrous resources by assigning rights of exclusive ownership; hence, property rights should extend to bitcoin. The article also discusses the implications of recognizing bitcoin as an ownable scarce resource within a private law society and addresses the challenges associated with penalizing bitcoin theft.
There has been tremendous interest invested by researchers and academics in Bitcoin since it's introduction to the financial market. However, in recent years there has been an advancement of the cryptocurrency market where other cryptocurrencies such as Ethereum, Litecoin and Ripple have grown relatively quickly and could potentially challenge the dominant placement of Bitcoin. These cryprocurrencies have been utilized globally as a virtual currency for multiple transactions. The returns of cryptocurrencies are known to be volatile and have been observed to fluctuate quite a bit in recent times. This study assesses and differentiates the performance of generalized autoregressive score (GAS) models integrated with a few heavy-tailed distributions in Value-at-Risk (VaR) estimation of the four most popular cryptocurrencies' returns, i.e. Bitcoin returns, Ethereum returns, Litecoin returns and Ripple returns. This paper proposed VaR models for Bitcoin, Ethereum, Litecoin and Ripple returns, i.e. GAS models combined with the generalized hyperbolic distribution (GHD), the variance gamma (VG) distribution, the normal inverse Gaussian (NIG) distribution and the generalized lambda distribution (GLD). The Kupiec likelihood ratio test was adopted to evaluate the proposed models' adequacy and Backtesting VaR was used to select the superior set of models.
This paper presents a comprehensive analysis of the historical progression, current trends, and prospects of Big Data. It explores the technological advancements that have established Big Data as a critical element of contemporary analytics, its extensive impact across various sectors, and the ethical challenges it poses. Beginning with the early recognition of Big Data's potential in the 2000s, the paper traces the development of foundational technologies such as Hadoop and the subsequent diversification of tools and methods. It delves into the integration of advanced analytics and machine learning, the rise of cloud-based Big Data services, and the transformative effects on sectors including healthcare, finance, agriculture, and education. The study also examines ethical considerations such as privacy, bias, transparency, and regulatory compliance, emphasizing the need for robust governance frameworks. It investigates the potential of emerging technologies like AI, IoT, and quantum computing to enhance Big Data capabilities further. It highlights future directions, including decentralized data ecosystems, advanced analytical techniques, and enhanced data privacy measures. By providing a panoramic view of Big Data's development, this paper aims to showcase its potential to revolutionize decision-making processes, improve operational efficiency, and drive innovation across industries; it underscores the importance of balancing technological innovation with ethical responsibility to ensure positive societal advancement and global progress. To add a novelty to the discussion, an AI agent Big D was created to provide a relevant analysis of trends in Big Data. The agent uses a multimodal ChatGPT-4o Large Language Model (LLM) from OpenAI and provides its review based on uploaded files and LLM knowledge.
Payments cog the wheels of the financial system. Beyond the payment initiation process lies a largely invisible, complex, and systemically important network of payment systems, which involves central banks, commercial banks and other payment providers. From a contemporary perspective, existing user needs in the field of payments can in principle be met by today’s centralized systems. Blockchain and its payment assets can maybe offer the same service level but are not superior to the more traditional payment solutions out there. Fast forwarding to the future, one could imagine a scenario where the technology around blockchain and its payment assets matures further and changes to business and user needs, especially in the fields of Decentralized Finance, the Metaverse, or Web 3.0, demanding features for which traditional payment rails are not an obvious choice anymore.
Kulvinder Singh, R. P. S. Tomar, Vansh Chaudhary, Mridul Jain
The cloud-based meteorological data management offers vast potential for research and collaboration, but inherent privacy concerns and data integrity risks necessitate robust solutions. This research suggests a new, multi-layered method to improve integrity and privacy in this field. By utilizing homomorphic encryption, this study makes it possible to perform calculations on encrypted meteorological data while keeping private information hidden from cloud service providers. Federated learning promotes cooperation without compromising the privacy of raw data by enabling distributed learning on local datasets. Lastly, zero-knowledge proofs are integrated to confirm the accuracy of computations made on encrypted data, ensuring the validity of outcomes without disclosing the underlying data. This integrated strategy presents a viable path for reliable and safe cloud-based meteorological data administration, promoting cutting-edge study and creativity while protecting private data.
Secure Electronic Healthcare Records (EHR) data is critical for protecting patient privacy and safeguarding the integrity of medical information. The requirement for strong security measures in healthcare data stems from the sensitive nature of the information involved, which includes personal identifiers and medical histories. This study explores existing techniques to securing healthcare data, outlining their shortcomings and proposing a unique methodology to address these difficulties. To manage healthcare data, the study takes a multimodal approach. It starts from the Synthea TM dataset and uses BERT -CNN for standardization. Game theory-based hyperparameter adjustment is used to maximize its performance. Full homomorphic encryption (TFHE) is then included for improved data security. Using RESTful API on the Ethereum blockchain, authentication is strengthened. An additional degree of protection is added with homomorphic encryption using decentralized identifiers. With the use of blockchain and homomorphic encryption, cloud infrastructure provides scalable and secure health data storage. Integrating the Ethereum blockchain strengthens storage that is both secure and decentralized. Using advanced technologies, this complete technique tackles the difficulties of security, standardization, and storage in the administration of healthcare data. Scalability, accessibility, and strict security requirements are met by this integrated method, which ensures standardized, safe, and privacy-preserving healthcare data management. With an average increase of almost 23%, the suggested Game Theory (GT) with BERT -CNN (99%) approach shows a significant improvement in accuracy over the current methods. The usefulness of the proposed model in improving the accuracy of the classification task over BERT and Random Forest approaches is highlighted by this noteworthy development, as demonstrated by the stated accuracy percentages. Together, these initiatives aim to bring about in a future in which patient outcomes are significantly improved by the secure handling, storage, analysis, and responsible use of medical data across the healthcare ecosystem.
Abstract Bitcoin and Ethereum are the two largest cryptocurrencies in the world by market capitalization and trading volume and the most popular despite high price fluctuations. This paper analyzes the relationship between Bitcoin and Ethereum metrics and the internet search interest on cryptocurrencies. As the literature shows, Google searches signal investor attention and Google Trends has proven useful for nowcasting economic and financial indicators. We aim to find the impact of Google Trends on Bitcoin and Ethereum prices, trading volumes and market capitalization since 2015 and discuss the potential correlations and patterns that may exist between these metrics and Google search interest. Through correlation and time-series analysis, we provide insights into the dynamics of this relationship and its implications for understanding cryptocurrency market behavior. The interest in cryptocurrencies tracked by Google Trends is a good indicator of measuring the social interest in the cryptocurrency market that drives a price movement. On the other hand, the price fluctuations of Bitcoin and Ethereum generate media and social attention and increase the interest in these cryptocurrencies. We also observe a positive effect of Google Trends values on trading volumes. The findings could help investors to understand the cryptocurrencies dynamics and build their trading strategies and could be of special interest to policymakers.
This research paper explores the intersection of zero-knowledge proofs (ZKPs) and machine learning (ML), presenting a comprehensive overview of recent advancements, applications, and challenges in this fast growing area. The jointers of ZKPs and ML techniques shall go a meter further to fuse privacy, security, and integrity in a number of solutions, which include forming of groups for data sharing and safe machine learning. Through the investigation of the well-respected sites in that area and also the thorough description of formulas and their experimental outcome, this paper looks for the clarification of the current state of affairs and the possible future directions of ZKPs in the AI world. By inserting the verification mechanism of ZKPs into machine learning ecosystem, it allows devising novel solutions for the problems of privacy and confidentiality that have for long been not solved. With this approach, the concatenation of parties collectively performs the process of dealing with private inputs without revealing any of these data and this, in return, opens the possibilities of secure multi-party computation. Furthermore, ZKPs protect data sharing as it gives people the opportunity to construct confidential data and share them to model training without compromising any one’s private details. Being a part of the dynamic conversations, which focus on the game-changing capacity of transparent zero-knowledge proofs (ZKPs), this paper brings the role of ZKPs in preserving the confidentiality and integrity of artificial intelligence (AI) applications into the centre of attention. As scientists still fight to improve protocols and circumvent computational complications, ZKPs are likely to establishment as critical tools in the effort to increase ML systems in the digital sphere.
Open access
Online Learning and Analytics
Intelligent Tutoring Systems and Adaptive Learning
With the rapid development of the Internet, the problem of network information security has become increasingly prominent. The traditional network security solutions have the weaknesses of centralization and vulnerability to attack, and cannot effectively deal with the risk of attack and data tampering. As a decentralized and tamper-resistant distributed ledger technology, blockchain technology has a good potential to be applied to network information security protection. This paper aims to summarize the basic principle and security characteristics of blockchain technology, discuss the network information security protection method based on blockchain, and analyze the application of blockchain technology in identity protection, food supply chain, O2O catering and other aspects for reference.
Yaoyue Tang, Karina Arias-Calluari, M. N. Najafi, Michael Harré · 5 authors
This paper analyses the high-frequency intraday Bitcoin dataset from 2019 to 2022. During this time frame, the Bitcoin market index exhibited two distinct periods, 2019-20 and 2021-22, characterized by an abrupt change in volatility. The Bitcoin price returns for both periods can be described by an anomalous diffusion process, transitioning from subdiffusion for short intervals to weak superdiffusion over longer time intervals. The characteristic features related to this anomalous behavior studied in the present paper include heavy tails, which can be described using a $q$-Gaussian distribution and correlations. When we sample the autocorrelation of absolute returns, we observe a power-law relationship, indicating time dependence in both periods initially. The ensemble autocorrelation of the returns decays rapidly. We fitted the autocorrelation with a power law to capture the decay and found that the second period experienced a slightly higher decay rate. The further study involves the analysis of endogenous effects within the Bitcoin time series, which are examined through detrending analysis. We found that both periods are multifractal and present self-similarity in the detrended probability density function (PDF). The Hurst exponent over short time intervals shifts from less than 0.5 ($\sim$ 0.42) in Period 1 to closer to 0.5 in Period 2 ($\sim$ 0.49), indicating that the market has gained efficiency over time.
A. Darwiesh, M. Elhoseny, A. H. El-Baz, Mohamed A. Nour
This study presents a new approach to predict cryptocurrencies risks based on social media platform indicators. This method can help cryptocurrency investors in their future decision-making. It utilizes advanced techniques such machine learning and natural language processing. Furthermore, a case study on American cryptocurrency investors is provided to help them identify and assess the risks associated with their purchases. Moreover, performance metrics are computed to demonstrate the capabilities of the new approach.
Bitcoin is one of those less common financial innovations that threatens to up-end the status quo in a more general sense. This not only instils fear in some decision-makers but loathing too. Which leads to an interesting question. That is, how does fear work itself into the construction of a Savage “Small World”? What happens if something terrifying is thought to be lurking in one of Weitzman’s boxes? Fear disrupts the very nature, the very structure, of search and decision.