Blockchain Papers

Frans Lavdari

No abstract is available for this record.

Hoseung Kang, Yeonchan Kang, Doojin Ryu, Robert I. Webb

This study evaluates machine learning models for forecasting daily Bitcoin returns using on-chain, macroeconomic, and market variables from January 2017 to December 2023. We implement a rolling-window framework with window lengths ranging from 365 to 730 days and compare several machine learning models against an autoregressive benchmark. Random Forest and Support Vector Machine achieve the lowest forecasting errors consistently across volatility regimes. Feature importance analysis using permutation importance and SHAP decomposition reveals that on-chain variables account for approximately 50 per cent of total forecasting contribution, with transaction fees and mining-related metrics ranking among the top important variables. Traditional market indicators such as VIX show limited relevance for Bitcoin return forecasting. These findings highlight the distinct informational value of blockchain-native variables for cryptocurrency forecasting.

Iida Hallikainen

Tutkimuksen taustalla oli kryptovaluuttojen kasvava merkitys rahoitusmarkkinoilla sekä spot-Bitcoin ETF -rahastojen käyttöönotto Yhdysvalloissa vuonna 2024. Uudet sijoitustuotteet ovat lisänneet yksityissijoittajien mahdollisuuksia saada altistusta Bitcoiniin, mutta samalla ne ovat tuoneet mukanaan uusia riskejä. Tutkimuksen tavoitteena oli tunnistaa spot-Bitcoin ETF -rahastoihin liittyvät keskeiset riskit sekä tarkastella riskienhallinnan keinoja yksityissijoittajan näkökulmasta. Tutkimus toteutettiin integroivana kirjallisuuskatsauksena. Aineisto koottiin Google Scholar- ja ScienceDirect-tietokannoista, ja se rajattiin pääosin vuosien 2024–2025 julkaisuihin. Mukaan valittiin tutkimuksia, jotka käsittelivät spot-Bitcoin ETF- ja ETP-tuotteiden riskejä ja riskimekanismeja. Aineisto analysoitiin vertailemalla tutkimusten keskeisiä havaintoja ja ryhmittelemällä ne laajem-miksi riskiluokiksi. Tulosten perusteella spot-Bitcoin ETF -rahastoihin liittyvät riskit voidaan jäsentää useaan pääluokkaan. Keskeisimpiä olivat volatiliteettiriski, likviditeetti- ja hinnoitteluriski, seuranta- ja rakenneriski, säilytys- ja operatiiviset riskit, sääntely- ja markkinarakenteen riskit sekä käyttäytymisriskit. Tutkimustulokset osoittivat, että ETF-rakenne ei poista Bitcoin-markkinoihin liittyvää voimakasta hinnanvaihtelua, ja että tuotteisiin liittyy myös rakenteellisia ja markkinamekanismeihin liittyviä epävarmuustekijöitä. Tulosten pohjalta muodostettiin yksityissijoittajalle suunnattu riskikehikko, joka kokoaa keskeiset riskit ja auttaa niiden jäsentämisessä. Johtopäätöksenä todettiin, että spot-Bitcoin ETF -rahastot tarjoavat yksityissijoittajalle helpomman ja säännellymmän tavan sijoittaa Bitcoiniin, mutta ne eivät poista sijoittamiseen liittyviä keskeisiä riskejä. Riskienhallinta edellyttää sijoittajalta tuotteen rakenteen ymmärtämistä, kriittistä tiedon arviointia sekä oman riskinsietokyvyn huomioimista. Lisäksi havaittiin, että osa riskeistä liittyy markkinarakenteeseen ja sääntelyyn, eikä niitä voida täysin hallita yksittäisen sijoittajan toimesta.

Fazal Danish

This OSF project hosts the pre‑registered live forecast for Bitcoin, published as part of Chapter 14 of the book The Luxury Collapse Threshold: How to Predict When Status Symbols Lose Their Power. The forecast was registered before the outcome was known. It includes: a full Luxury Risk Index (LRI) assessment of Bitcoin; an Early Warning Dashboard signal analysis; a predicted trajectory for 2026–2031; explicit confirmation and falsification criteria. This registration is intended to be permanently archived and publicly citable. Readers of the book are invited to verify the forecast and track its accuracy over time.

Pedro Cosme

No abstract is available for this record.

Patryk Chmielarz

Dynamiczny rozwój technologii rozproszonych rejestrów (DLT – Distributed Ledger Technology) oraz rosnące oczekiwania społeczne w zakresie transparentności finansów publicznych skłaniają do analizy możliwości wdrożenia technologii blockchain w systemie zarządzania wydatkami jednostek samorządu terytorialnego (JST). W artykule poddano ocenie potencjał blockchain jako narzędzia eliminującego asymetrię informacyjną i zwiększającego społeczną kontrolę nad finansami JST. Technologia ta, dzięki niezmienności rejestrów oraz kryptograficznemu potwierdzaniu transakcji, może przyczynić się do redukcji ryzyka korupcji i nadużyć budżetowych. Szczególną uwagę poświęcono aspektom prawnym implementacji blockchain w sektorze publicznym, w tym jego zgodności z ustawą o finansach publicznych, przepisami dotyczącymi zamówień publicznych oraz regulacjami RODO. W artykule przeprowadzono także analizę porównawczą międzynarodowych wdrożeń blockchain w administracji publicznej oraz zaproponowano model implementacji tej technologii w kontekście polskich JST.

Junhan Wang

Traditional technical solutions face inherent limitations in ensuring data ownership transparency, tamper-proofing, and traceability in data factor markets, particularly regarding core challenges like unclear ownership rights, high transaction costs, and trust deficits. This paper proposes and designs a blockchain-based data trust registration system. The system is theoretically grounded in the “three rights separation” framework of “rights bundles” and architecturally divided into six layers: data resource layer, storage layer, core layer, service layer, consensus and security layer, and application layer. It enables systematic processing and hierarchical interaction of complex data through progressive data trust certification, ownership transfer and traceability, and integrity verification. This establishes a collaborative, efficient, and trustworthy data registration infrastructure. By integrating on-chain and off-chain storage coordination, the system achieves efficient certification and secure balance of data rights. Additionally, the paper explores extended technologies like cross-chain interoperability and zero-knowledge proofs to address future needs for multi-chain coexistence and sensitive data registration. Ultimately, this solution aims to provide core technological support for building a trustworthy, efficient, and open data factor circulation environment, thereby reducing transaction trust costs and unlocking the latent economic value of data.

Jian Wang, Wenjing Gao, Weiwei Ma, Hao Xu · 6 authors

As the application of Embodied Intelligence deepens within the Industrial Internet of Things (IoT) domain, traditional centralized trust schemes are increasingly unable to meet the demand for establishing efficient trust among heterogeneous devices, due to risks like single points of failure, auditing difficulties, and privacy leakage. To address these issues, this paper proposes a trust and privacy-preserving framework based on blockchain and Zero-Knowledge Proof (ZKP). The framework establishes a decentralized trust foundation using Hyperledger Fabric. On this foundation, a Decentralized Identity (DID) system is implemented through smart contracts, assigning a unique and verifiable identity anchor to each Embodied Intelligence device. Furthermore, to reconcile auditability and data privacy, the framework integrates ZKP technology. This technology enables edge devices to locally generate and submit on-chain proofs of operational compliance, facilitating transparent auditing without disclosing sensitive data. Finally, to transform trustworthy behavior records into a quantifiable metric, the framework designs a dynamic reputation assessment mechanism. This mechanism uses smart contracts to automatically analyze the verified on-chain behavioral history, continuously updating the reputation score for each Embodied Intelligence device. A smart factory case study demonstrates the framework's practical application, while performance evaluation on a physical testbed confirms its efficiency and scalability for real-time industrial control.

MACEY-DARE, RUPERT

No abstract is available for this record.

Loso Judijanto, Apriyanto Apriyanto

This study conducts a scientometric analysis of global financial risk management research to map its intellectual structure, thematic trends, and collaboration networks over the period 2000–2025. Data were retrieved from the Scopus database using a comprehensive search strategy and analyzed with VOSviewer to visualize co-authorship patterns, country collaborations, keyword co-occurrences, thematic clusters, and temporal developments. The results indicate that risk management, risk assessment, and financial markets remain the most influential and frequently studied topics, while emerging themes such as sustainability, decentralized finance, cryptocurrency, and supply chain resilience reflect the field’s adaptation to evolving technological, economic, and environmental challenges. Collaboration analysis highlights the dominance of countries such as China, the United Kingdom, and India, alongside increasing participation from emerging economies. The study offers practical implications for policymakers and financial practitioners to align strategies with current research priorities, and theoretical contributions by identifying conceptual linkages and emerging research fronts. Limitations include reliance on a single database and the inherent biases of citation-based analysis.

Wei Heng, Yuze Zhang

The rapid digital transformation of the sports industry has opened up unprecedented opportunities for efficiency, transparency, and innovation. Traditional transaction models still suffer from significant challenges, including centralized control, lack of trust, and inefficiencies in revenue distribution. These issues often stem from reliance on intermediaries that introduce risks such as data manipulation, high operational costs, and delays in processing financial transactions. Blockchain technology presents a promising solution by enabling decentralized, secure, and transparent transactions, fostering greater trust among all stakeholders within the sports ecosystem. Existing approaches to digital transactions in the sports industry primarily depend on centralized financial institutions and third-party service providers, which not only limit transparency but also create barriers to financial inclusivity for athletes, clubs, sponsors, and fans. To address these critical limitations, we propose a blockchain-based digital transaction model that leverages smart contracts and distributed ledger technology (DLT) to enhance the efficiency, security, and fairness of transactions across the entire sports industry value chain. Our model integrates key economic principles with advanced network analysis to optimize revenue distribution, mitigate fraudulent activities, and enable real-time transaction verification. Through extensive simulations and empirical analysis, our results demonstrate a significant improvement in transaction speed, cost reduction, and overall transparency compared to conventional models. By decentralizing financial transactions, the proposed approach not only enhances financial inclusivity for all participants but also aligns with the broader vision of sustainable and equitable growth in the digital sports economy.

Dept of ECE IARE, Dadi Jagan Goud

Cryptocurrency price prediction has become crucial for informed trading decisions due to the volatile nature of assets like Bitcoin, Ethereum, Ripple, and Litecoin. Traditional methods like ARIMA and GARCH struggle with this volatility, while modern approaches such as machine learning and deep learning provide better accuracy. This study evaluates advanced models, including LSTM, GRU, and Light GBM, to predict cryptocurrency prices and assess trading strategies before and after the COVID-19 pandemic. GRU and LSTM excel at identifying patterns in price data, with GRU performing best for Ripple. Ensemble methods like Light GBM proved highly accurate for Bitcoin and Ethereum across time periods. Simpler models like RNN were sufficient for Ripple and Litecoin. The COVID-19 pandemic significantly impacted market dynamics, emphasizing the importance of precise predictions. Trading strategies based on model predictions showed that ensemble methods like Light GBM yielded the highest profitability post-pandemic. The findings highlight the need to tailor models to specific cryptocurrencies and market conditions. Improved deep learning tools can enhance trading efficiency and provide actionable insights for investors and policymakers. Future research could focus on predicting multiple cryptocurrencies simultaneously and optimizing portfolio-based trading strategies. Key Words: LSTM, ARIMA, GARCH, RNN

Drissia Ennagoura, Kamal El Kehal, Khalid El Fahssi, Mohamed El Far · 7 authors

It is difficult to predict cryptocurrency market trends due to volatility and extraneous factors. In this study, the XGBoost and LSTM models are contrasted in terms of forecasting bullish and bearish trends in the Ethereum market. Technical indicators like Simple Moving Average (SMA), Exponential Moving Average (EMA), and trading volume were employed as features based on past market data. Market tendencies were established through changes in closing price on a day-to-day basis, and training and testing the two models applied was carried out on normalized data under supervised learning. Results in experiments show that XGBoost exhibited superior performance at 84.58%, which was entirely above the 50.45% achieved using LSTM. The differential in performance implicates superior performance by XGBoost in establishing nonlinear relations among input features and market tendencies. The results show that XGBoost is more suitable for market trend classification, while LSTM cannot generalize and overfit time-series patterns. The results offer possibilities for sequential model enhancement by employing more technical indicators or hybrid architectures that combine time-series analysis and ensemble learning techniques.

Harshraj Bhoite

This document provides a comprehensive analysis of sustainable data engineering practices, focusing on the ecological implications of contemporary methodologies. It examines power usage, carbon dioxide output, and electronic waste production in data centers, while exploring eco-friendly approaches such as energy-conserving hardware, streamlined data handling processes, and the adoption of sustainable power sources. The potential of AI enhanced optimization techniques, quantum computation, and distributed ledger systems to reduce environmental impact is also examined. The paper concludes with actionable strategies for corporations and regulators to enhance the sustainability of data engineering practices, ensuring that the expansion of our digital landscape does not occur at the cost of environmental health.

H. Hashmi, Ahmet Faruk Aysan, Hassnian Ali

This study explores the transformative impact of Donald Trump’s 2024 US presidential victory on digital currency markets and regulatory frameworks. Trump’s administration, opposing central bank digital currencies (CBDCs) and championing decentralized financial systems, signifies a stark shift from the Biden administration’s cautious exploration of CBDCs. Utilizing lexicon and rule-based sentiment analysis through the valence aware dictionary and sentiment reasoner (VADER), the research quantitatively assesses shifts in political rhetoric and public sentiment. Market dynamics, including Bitcoin’s surge to $100,000, highlight Trump’s repositioning as a proponent of decentralized finance, framing CBDCs as instruments of “government tyranny” aligned with libertarian ideals. The findings indicate Trump’s policies may position the US as a cryptocurrency innovation hub while stalling federal CBDC initiatives, with far-reaching implications for global financial systems. This analysis informs debates on regulatory priorities, financial sovereignty and the US’s geopolitical role in the digital currency race.

Umar Al Faruq, Dwi Fitrizal Salim, Farida Titik Kristanti

This study conducted a large-scale analysis to evaluate the performance of traditional and Markov-Switching GARCH (MS-GARCH) models to estimate the volatility of the top 10 cryptocurrencies by market capitalization. The study compared the performance of the models using goodness-of-fit measures, specifically the Deviance Information Criterion (DIC) and the Bayesian Predictive Information Criterion (BPC). Secondly, we assess the forecasting accuracy for one-day-ahead conditional volatility and Value-at-Risk (VaR). The results obtained show that, in a manner consistent with the findings for the broader cryptocurrency market, the time-varying regime-switching model exhibits superior performance in capturing the complex volatility patterns observed in cryptocurrencies when compared to the traditional GARCH model.

Zhihan Xu, Xinyue Zhang, Zili Zhou

Recently, with the gradual development of machine learning technology, more and more people are trying to apply machine learning technology in various fields, and finance is one of the important fields. This work investigates the optimization of cryptocurrency portfolios by combining Long Short-Term Memory (LSTM) time series forecasting with traditional portfolio optimization methods. The focus of the paper is on using the historical price data from the past six years of Bitcoin (BTC), Ethereum (ETH), and Litecoin (LTC) to train LSTM models, which are then used to predict the prices of these cryptocurrencies for the period from January to June 2024. These predictions are subsequently incorporated into an extended Markowitz framework to optimize the portfolio on a monthly basis. The results indicate that the LSTM-enhanced portfolio optimization method yields higher returns and better risk management compared to traditional methods. This finding could prove that it is feasible and effective to apply machine learning methods, especially time series forecasting methods, to cryptocurrency portfolios.

Luiz Koodi Hotta, Carlos Trucíos, Pedro L. Valls Pereira, Mauricio Zevallos

Recent studies have suggested that more complex models than GARCH are better suited for forecasting cryptocurrency risk measures, such as Value-at-Risk and Expected Shortfall. Among these studies, some highlight the advantages of MSGARCH models over traditional GARCH models. While improvements over single-regime GARCH models have been observed by using MSGARCH, the literature has only focused on the MSGARCH specification proposed by Haas, Mittnik and Paolella (Journal of Financial Econometrics, 2004) overlooking several other well-established MSGARCH specification alternatives. In this paper, we illustrate that exploring alternative MSGARCH specifications can lead to improvements in risk measure performance, emphasizing the potential benefits of using several specifications.

Fátima Rodrigues, Miguel P. Machado

The cryptocurrency market is currently one of the most interesting areas for investment, attracting both experienced and casual investors. Although it can offer high returns, it also poses significant risks due to its high volatility. In this context, artificial intelligence, particularly through deep learning and machine learning algorithms, has played a key role in developing applications that provide investment advice, with the aim of maximizing returns and reducing investment risks. This study proposes a system for forecasting the closing prices of ten of the leading cryptocurrencies currently available in the market, presented in a web application capable of making predictions ranging from one to four hours. To achieve this, different models using various machine learning and deep learning algorithms were analyzed and tested, including Recurrent Neural Networks, time series analysis algorithms such as ARIMA, and even some more conventional regression algorithms. For algorithm comparison, minute step Bitcoin price data over a 30-day period was used to forecast prices 60 minutes ahead. Through extensive experimentation, the GRU neural network demonstrated superior predictive accuracy, achieving MAPE = 0.09\%, MSE = 5954.89, RMSE = 77.17, and MAE = 60.20. A web application was also developed, which integrates the best-performing model to provide real-time price predictions for multiple cryptocurrencies.

Bilal Khan, Ali Rizwan Hashmi

In an era where digitalization has dominated the financial world, cryptographic methods have become the foundation of secure transactions and data integrity. This report conducts an in-depth analysis of the cryptographic methods used in modern cryptocurrencies, namely Bitcoin and Ethereum, and traditional banking systems. The strengths, limitations and implications regarding security and scalability will be highlighted. Bitcoin, employing the usage of Elliptic Curve Cryptography (ECC) and the Secure Hash Algorithm (SHA-256) offers a robust and decentralized architecture heavily resistant to modern threats such as brute force attacks, as well as future threats that may arise with the rapid development of quantum computing. Ethereum takes the fundamental principles of Bitcoin, and enhances them with innovations like Keccak-256, and Recursive Length Prefix (RLP) encoding, optimizing the security and efficiency for complex operations such as smart contracts. Comparatively, traditional banking systems utilize a hybridized cryptographic system, incorporating the usage of methods like AES and ECC to balance security with performance within a centralized financial system, however often constrained by the vulnerabilities methods like AES brings, such as information leakage and overall human error. This comparative analysis highlights the trade-offs between these three systems, offering critical insights into the rapidly evolving role that cryptography is taking in shaping the future of the financial world. The findings presented in this report offer actionable recommendations for advancing cryptographic techniques and adopting decentralized systems to enhance the resilience of commonly used financial systems out in the world today.

Saeed Mohammadi Dashtaki, Mehdi Hosseini Chagahi, Aein Bahadori, Behzad Moshiri · 6 authors

Cryptocurrency markets are highly volatile and sentiment-driven, posing challenges to traditional forecasting methods. This paper presents Hard and Soft Information Fusion (HSIF), a novel Transformer-based dual-stream model that combines market data and social sentiment using Financial Bidirectional Encoder Representations from Transformers (FinBERT), a financial sentiment analysis tool, and a bidirectional cross-attention mechanism. Evaluations on multi-year Bitcoin data show that HSIF achieves 97.48% accuracy and a 26.64% return, outperforming Long Short-Term Memory (LSTM)-based and other multimodal models. The results highlight the effectiveness of domain-specific sentiment embeddings and cross-modal attention in enhancing trend prediction accuracy for volatile cryptocurrency markets.

Lihua Zhang, Jiayi Bai, Yi Yang, Wenbiao Wang · 5 authors

No abstract is available for this record.

Maksim Teterin, Anatoly Peresetsky

Since the introduction of Bitcoin in 2008, the size of the cryptocurrency market is becoming increasingly important for investors. Thus, the forecast of cryptocurrency price volatility is of particular interest to portfolio investors, as they are interested in accurately estimating the standard deviation of their portfolios to calculate the Value-at- Risk (VaR) as a risk measure for more optimal portfolio management. The HAR-RV model introduced by F. Corsi (in 2009) became more effective than the traditional GARCH type models in forecasting in the volatility of fi nancial assets. In the last decade, cryptocurrencies started to dominate both the social media and the fi nancial press. At the same time, some academic papers use social media data to enhance the cryptocurrency volatility forecasting models. In our paper, we study how the use of Google Trends data could improve the precision of one-day-ahead of Bitcoin price volatility models forecasts. We use three different measures of the forecast precision. All models are estimated in rolling windows in order to control for possible structural breaks. Also, we estimate the optimal length of rolling windows to provide the best forecast precision on the historical Bitcoin price data from January 1, 2018 to December 31, 2022. We verify that the predictive power of the chosen model statistically differs from other models via MCS-test. С появлением в 2008 г. биткоина размер рынка криптовалют вырос и стал важным для инвесторов. Таким образом, сегодня прогноз волатильности цены криптовалюты является предметом особого интереса для портфельных инвесторов, поскольку они заинтересованы в точной оценке стандартного отклонения их инвестиционных портфелей для вычисления сумм под риском (VaR) как меры риска для оптимального управления портфелем. HAR-RV-модель, предложенная F. Corsi (в 2009 г.), показала бóльшую эффективность при прогнозировании волатильности финансовых активов по сравнению с более традиционными моделями из семейства GARCH. В последнее десятилетие сообщения и статьи о криптовалютах стали все чаще появляться как в социальных медиа, так и в финансовой прессе. В то же время в некоторых академических исследованиях авторы используют данные социальных медиа для улучшения моделей прогноза волатильности криптовалют. В данной работе мы проводим анализ того, как использование данных Google Trends могут повысить точность моделей для однодневного прогноза волатильности цены биткоина. В исследовании мы используем три различные меры точности прогнозов. Все модели оцениваются в скользящих окнах для контроля на наличие структурных сдвигов в данных. Также мы подбираем оптимальный размер скользящего окна для получения наилучшего прогноза на исторических данных цены биткоина с 01.01.2018 по 31.12.2022. С помощью MCS-теста мы показываем, что прогнозная сила выбираемой модели статистически отличается от других.

Amit Kumar, Taoran Ji

Cryptocurrencies fluctuate in markets with high price volatility, which becomes a great challenge for investors. To aid investors in making informed decisions, systems predicting cryptocurrency market movements have been developed, commonly framed as feature-driven regression problems that focus solely on historical patterns favored by domain experts. However, these methods overlook three critical factors that significantly influence the cryptocurrency market dynamics: 1) the macro investing environment, reflected in major cryptocurrency fluctuations, which can affect investors’ collaborative behaviors, 2) overall market sentiment, heavily influenced by news, which impacts investors’ strategies, and 3) technical indicators, which offer insights into overbought or oversold conditions, momentum, and market trends are often ignored despite their relevance in shaping short-term price movements. In this paper, we propose a dual prediction mechanism that enables the model to forecast the next day’s closing price by incorporating macroeconomic fluctuations, technical indicators, and individual cryptocurrency price changes. Furthermore, we introduce a novel refinement mechanism that enhances the prediction through market sentiment-based rescaling and fusion. In experiments, the proposed model achieves state-of-the-art performance (SOTA), consistently outperforming ten comparison methods in most cases. Our code and data can be found at https://github.com/aamitssharma07/SAL-Cryptopulse