Blockchain Papers

Jean Chrysostome NDAYISABYE

No abstract is available for this record.

Antonio Pellicani, Gianvito Pio, Sašo Džeroski, Michelangelo Ceci

Abstract The cryptocurrency market represents a significant innovation in the financial ecosystem, built upon cryptographic principles to ensure secure and transparent transactions. Cryptocurrencies experienced a global adoption, driven by their decentralized nature that enables borderless transactions without third-party intermediaries. The price of cryptocurrencies is characterized by a significant volatility, that introduces both opportunities and challenges. In this context, the development of accurate methods for the forecasting of price variation, able to work in real-time on data streams, has become vital for various stakeholders. In this paper, we propose a novel approach, called LEMON, for the online prediction of the price variation of cryptocurrencies, that leverages possible temporal correlations among them. Our approach stems from the empirical evidence that cryptocurrencies tend to form groups characterized by similar trends, a behavior often attributed to shared market dynamics and common external factors. Through the analysis of temporal correlations, LEMON dynamically identifies these groups, that are then exploited to learn multiple multi-target tree-based models, specifically designed for processing continuous data streams. LEMON also introduces a novel adaptive non-parametric weighting scheme, that automatically adjusts the importance of each instance based on the observed data distribution in real-time, improving the forecasting of the price variation. Our experiments, performed on 16 datasets related to 16 cryptocurrencies, demonstrate that LEMON outperforms state-of-the-art approaches in two distinct prediction tasks: forecasting the closing price variation (regression) and predicting the market trend direction (classification), making it an effective tool to support stakeholders requiring accurate real-time predictions.

A. B. Hajira Be A. B. Hajira Be, S.Bhuvaneshwari S.Bhuvaneshwari, Sankari.S Sankari.S

Cryptocurrency markets have gained significant global attention due to their decentralized nature and high financial value. Among various cryptocurrencies, Bitcoin is the most widely traded and exhibits highly volatile price behavior. Accurate analysis and prediction of Bitcoin price trends are challenging because the market is influenced by rapid trading activities, large data streams, and complex temporal patterns. This paper presents a streaming data collection and analysis system for Bitcoin using the Long Short-Term Memory (LSTM) deep learning algorithm. The proposed system continuously collects real-time Bitcoin market data from online cryptocurrency exchanges through streaming APIs. The collected data is then preprocessed and analyzed using an LSTM-based predictive model capable of learning long-term dependencies in time-series data. The LSTM network processes sequential historical price data to forecast future market trends and provide analytical insights into Bitcoin price movements. The system integrates data acquisition, preprocessing, deep learning-based prediction, and visualization modules to create an efficient cryptocurrency analysis framework. The proposed approach focuses on improving prediction accuracy by combining real-time streaming data with advanced neural network models. This system can assist researchers, financial analysts, and investors in understanding cryptocurrency market behavior and making informed trading decisions. The proposed design demonstrates the feasibility of integrating streaming data technologies with deep learning models for real-time financial market analysis. Keywords— Cryptocurrency, Bitcoin, Streaming Data, LSTM Algorithm, Deep Learning, Time-Series Prediction, Financial Data Analysis.

SquirrelSniper138

THE SS138 PROTOCOL: A DETERMINISTIC INGRESS ARCHITECTURE FOR DISTRIBUTED DATA DRIFT ISOLATION Abstract — This paper introduces the SS138 protocol, an invariant edge gateway architecture designed to isolate and eliminate calculation variance, packet time-series anomalies, and systemic tracking drift before data reaches downstream processing components. The architecture provides an application-layer structural filter, mapping incoming data vectors onto a fixed coordinate system bound by a multi-phase temporal macro framework. By evaluating metrics across structured phase intervals, the protocol achieves deterministic input sanitization and real-time entropy tracking with minimum algorithmic overhead, reducing the attack surface and protecting downstream distributed ledgers from processing failures or data propagation errors. Owner and Developer SquirrelSniper138 from YouTube

Simona-Vasilica Oprea, Adela BÂRA

Abstract This research presents a regime-aware hybrid forecasting framework for the Bitcoin market’s nonlinear, nonstationary and regime-switching behavior. The architecture integrates econometric models, neural forecasting and meta-learning, unified under a regime-detection mechanism using probabilistic inference. Central to the approach is a Hidden Markov Model (HMM) trained on log returns, which infers latent market regimes, bull, bear and sideways, based on statistical characteristics rather than arbitrary thresholds. Each detected regime triggers a specialized forecasting model: ARIMAX for volatile bear markets, SARIMAX for cyclical sideways periods and NeuralProphet for nonlinear bullish dynamics. These models leverage historical returns (Jan. 2012-Jun. 2025) and external signals, including technical indicators (RSI, MACD, Bollinger bands) and volatility metrics. A meta-learning layer, implemented via XGBoost, dynamically selects the optimal model at each time step based on the regime. This enables real-time adaptation to evolving market conditions. Predictions are made on log returns and translated into price forecasts through exponentiation. The framework’s performance is evaluated using R 2 , Mean Absolute Error (MAE) and Root Mean Squared Error (RMSE). The regime-aware model outperforms the no-regime model significantly across all metrics, especially in error reduction (MAE cut by ~ 56%) and higher explanatory power (R² increased from 0.82 to 0.91). Ablation results confirm the structural validity of the proposed framework, with the regime–model assignment (ARIMAX for bear, SARIMAX for sideways, NeuralProphet for bull) achieving the lowest forecasting error (MAE = 736, R 2 = 0.93) at the yearly level and outperforming alternative configurations. The inferred regimes exhibit economically meaningful persistence (average durations 14.8–22.4 days) and transition stability (diagonal probabilities 0.91–0.94). The meta-learning component shows coherent and interpretable behavior, with regime labels and recent model errors explaining nearly 70% of decision weight and regime-consistent model selection exceeding 80%. These forecasting gains translate into tangible economic benefits: in a six-month backtest, the proposed strategy delivers the highest return (19%), lowest drawdown (19%) and highest Sharpe ratio (1.01), outperforming all benchmarks.

N Sudha, A Lakshmisri

The accelerating digitization of financial services has transformed global economic ecosystems while simultaneously amplifying the scale, speed, and structural complexity of financial fraud. Real-time payments, open banking infrastructures, fintech platforms, and decentralized finance environments have expanded transactional connectivity, creating highly dynamic and interconnected risk landscapes. Conventional rule-based and standalone machine learning systems demonstrate limited effectiveness against adaptive adversaries, coordinated fraud rings, synthetic identity schemes, and cross-platform laundering networks. Advanced detection strategies require intelligent architectures capable of modeling temporal behavior, relational dependencies, and large-scale streaming data within production-grade environments. This chapter presents a comprehensive framework for next-generation financial fraud detection integrating Artificial Intelligence, Deep Learning, and Graph Analytics. The discussion synthesizes supervised, unsupervised, and semi-supervised learning approaches with sequential deep learning architectures, transformer-based models, and graph neural networks for network-aware inference. Emphasis is placed on hierarchical multi-stage detection systems, cloud-native deployment strategies, adversarial robustness, privacy-preserving computation, and real-world validation methodologies. Critical challenges such as extreme class imbalance, concept drift, scalability of graph processing, explainability under regulatory constraints, and cross-institution collaboration are systematically examined. A unified hybrid AI–graph intelligence architecture is articulated to address both transactional anomalies and coordinated fraud ecosystems. The chapter contributes a structured taxonomy of modern financial fraud, an integrated modeling perspective combining temporal and structural intelligence, and a deployment-oriented evaluation framework aligned with real-world financial operations. By bridging theoretical advancements with production-grade implementation considerations, this work establishes a rigorous foundation for scalable, interpretable, and resilient fraud detection systems within evolving digital financial infrastructures.

Sattar

Cryptocurrencies have upended the financial industry since they provide decentralized and peer-to-peer transactions. However, due to market volatility and the numerous non-linear relationships between price dynamics and human mood, forecasting Bitcoin values is a difficult task. The deep learning architecture shown in this work combines sentiment confidence scores derived from cryptocurrency-related tweets utilizing Transformer-based natural language processing with historical price indicators. The model incorporates Convolutional Neural Networks (CNN) to detect local time-series patterns and Long Short-Term Memory (LSTM) networks to produce long-term dependencies. We apply this architecture, involving sequence-based preprocessing and normalization, to Bitcoin and Ethereum to ensure robustness. Evaluations in comparison to baseline models Sentiment fusion dramatically increases predicting accuracy, especially during times of market turbulence, according to CNN-LSTM without sentiment, vanilla LSTM, and ARIMA. Our research helps develop scalable, sentiment-aware financial forecasting algorithms that better reflect the behavior of real markets.

Muskan Sureka, Aadi Poddar, Debolina Ghosh, Sonal Jain · 6 authors

Bitcoin and other Crypto-Currency Price Prediction has been a concern for many financial analytics and business owners. This becomes critically important due to the volatile nature of the Bitcoin. This paper focuses on predicting the next-day Bitcoin price predictions using historical OHLC data from 2019 to 2024 using eleven machine learning algorithms. We have applied fourteen technical features including moving averages, volatility indicators, and lag variables to capture market statistics and price fluctuations. Models that were used in this paper include linear methods (Linear, Ridge, and Lasso regression), ensemble techniques (Random Forest, XGBoost, Gradient Boosting, AdaBoost), instance-based learning (KNN), support vector machines (SVR), decision trees, and deep learning (LSTM networks). Robust performance is ensured by the Five-fold cross-validation. The results clearly show that Lasso regression outperforms other algorithms with a RMSE of $727.33 and R2of 0.971, achieving superior performance in comparison to complex ensemble methods.

Piotr Fiszeder, Witold Orzeszko, Radosław Pietrzyk, Grzegorz Dudek

This study advances the understanding of Bitcoin volatility forecasting by analysing an extensive set of 62 explanatory variables, including cryptocurrency market behaviour, Google search trends, financial indices, and economic indicators. We employ Bayesian Model Averaging (BMA), Least Absolute Shrinkage and Selection Operator (LASSO), and Random Forest (RF) methods to assess variable importance and forecast accuracy. Our research demonstrates that LASSO and RF models incorporating exogenous variables significantly improve both daily and weekly Bitcoin variance forecasts compared to models using only lagged Bitcoin volatilities. Key factors influencing Bitcoin volatility include lagged realised variances, trading volume, and Google search intensity. The study reveals that the impact of these variables on Bitcoin volatility is time-varying, reflecting its evolving relationship with broader economic indicators and market sentiment. Our findings contribute to the literature by providing a comprehensive analysis of Bitcoin volatility drivers, evaluating the effectiveness of variable transformations, and comparing the performance of advanced forecasting methods in handling the cryptocurrency's extreme volatility. These insights are valuable for researchers, investors, portfolio managers, and policymakers navigating the dynamic cryptocurrency market.

Arthur G. Bubolz, Marcos C. Freitas, Giancarlo Lucca, Rafael A. Berri · 6 authors

No abstract is available for this record.

S Ezhilmathi, S. Selvakumara Samy

No abstract is available for this record.

Fabricio Marcillo, Melissa Quiñonez, Patricio Neptali Vaca Escobar, Graciela Trujillo

El estudio analizó el comportamiento de las criptomonedas Bitcoin y Ethereum durante el año 2024 mediante la construcción de un modelo estadístico ARIMA (AutoRegressive Integrated Moving Average). La investigación utilizó un enfoque cuantitativo que se dividió en cuatro etapas: recopilación y limpieza de datos históricos, verificación de la estabilidad de los datos, identificación y estimación de los mejores parámetros usando criterios de información, y validación mediante medidas de precisión y análisis de residuos. Los resultados demostraron que el modelo ARIMA fue útil en el pronóstico de valores en mercados estables, destacando su trayectoria en el análisis de datos financieros. Además, los valores bajos de RMSE y MAPE validaron que el modelo tiene la capacidad de realizar pronósticos precisos en escenarios con alta frecuencia. En particular, el MAPE de Bitcoin fue 2,25 % y el de Ethereum 2,85 % durante la etapa de prueba, demostrando que los valores pronosticados tuvieron una ligera desviación con respecto a los reales. No obstante, el modelo puede verse afectado en periodos de alta volatilidad, como en las burbujas especulativas o en los desplomes bursátiles, ya que no tiene la capacidad de adaptarse dinámicamente a cambios súbitos en los parámetros; sin embargo, su utilidad puede mejorar al combinar modelos híbridos con ARIMA.

Bo Xiao, Wei Yin

Bitcoin transaction anomaly detection is essential for maintaining financial market stability. A significant challenge is capturing the dynamically evolving transaction patterns within transaction networks. Dynamic graph models are effective for characterizing the temporal evolution of transaction systems. However, current methods struggle to mine long-range temporal dependencies and address the class imbalance caused by the scarcity of abnormal samples. To address these issues, we propose a novel approach, the Bidirectional EvolveGCN with Class-Balanced Learning Network (Balanced-BiEGCN), for Bitcoin transaction anomaly detection. This model integrates two key components: (1) a bidirectional temporal feature fusion mechanism (Bi-EvolveGCN) that enhances the capture of long-range temporal dependencies and (2) a Sample Class Transformation (CSCT) classifier that generates difficult-to-distinguish abnormal samples to balance the positive and negative class distribution. The generation of these samples is guided by two loss functions: the adjacency distance adaptive loss function and the symmetric space adjustment loss function, which optimize the spatial distribution and confusion of abnormal samples. Experimental results on the Elliptic dataset demonstrate that Balanced-BiEGCN outperforms existing baseline methods in anomaly detection.

Inas Al Khatib, Malick Ndiaye

Bad medical debt negatively impacts individuals' physical and mental well-being, can discourage future care-seeking, and is increasingly viewed as a social determinant of health. Addressing this issue by linking the healthcare sector with humanitarian efforts presents a significant global challenge, requiring innovative solutions. This paper aims to synthesize existing literature on the topic. Using the Scopus database, a systematic review of literature was conducted from 1990 to 2024, employing the PRISMA framework. Thematic analysis was applied to organize and interpret the findings. Reviewing 958 papers, including 318 key sources, revealed a pressing need for a SMART blockchain healthcare platform. Such a platform would securely connect beneficiaries with philanthropists, facilitate data sharing, and align donor requirements with beneficiary criteria. Employing decentralized autonomous organization frameworks and smart contracts ensures transparency, efficiency, and accountability through automated and secure processes.

Adi Suryaputra Paramitha

Gas fees play a crucial role in Ethereum blockchain transactions, directly affecting the cost and efficiency of decentralized applications. This study analyzes gas fee patterns across transaction types, temporal trends, and anomalous behaviors using a dataset of 1,000 Ethereum transactions. The results reveal that the average gas price was 120.5 Gwei, with a standard deviation of 45.2 Gwei, highlighting significant variability. Smart contract functions exhibited varying gas usage, with mint operations consuming the highest average gas (1,500,000 units) compared to approve (1,200,000 units) and transfer (800,000 units). A positive correlation (r = 0.65) was observed between gas price and value transferred, suggesting that higher-value transactions often incur elevated gas fees. Temporal analysis showed predictable patterns, with peak gas prices occurring between 13:00 - 17:00 UTC during high network activity and lower prices between 02:00 - 06:00 UTC. Additionally, anomaly detection identified 15 outlier transactions, including one with an unusually high gas price of 500 Gwei, reflecting network congestion or prioritization strategies. These findings provide actionable insights for optimizing transaction costs and improving smart contract efficiency. Future research could explore layer-2 scaling solutions, alternative fee mechanisms, and machine learning approaches for gas price prediction. This study contributes to a deeper understanding of Ethereum’s gas fee dynamics, offering valuable guidance for developers, users, and researchers in the blockchain ecosystem.

Thi Thanh Thuy, Minh‐Ky Nguyen, Thuyet D. Bui, Hoang Phan Hải Yen · 10 authors

This paper explores how blockchain technology, widely known as the backbone of cryptocurrencies, can be harnessed to address limitations of traditional water quality monitoring (WQM) systems. Blockchain offers a decentralized, tamper-proof ledger that enables secure, transparent, and traceable data management across distributed networks. When applied to water quality monitoring, blockchain facilitates real-time data acquisition, enhances data integrity, and enables smart contracts for automated regulatory compliance and alerts. These features not only improve the accuracy and efficiency of WQM systems but also build public trust in the reported data. Key insights from current research and pilot applications highlight blockchain’s capacity to integrate with IoT devices for real-time sensing, support adaptive water governance, and empower local stakeholders through decentralized control and transparent access to information. The implications for policy and practice are significant: blockchain-based WQM can support stronger regulatory enforcement, encourage cross-sector collaboration, and provide a robust digital foundation for sustainable water management in smart cities and rural areas alike. As such, this review paper positions blockchain as a transformative tool in the digital transition toward more resilient and equitable water management systems.

Amrendra Singh Yadav, Vincent Charles, Tatiana Gherman, Vinay Kumar · 6 authors

The manufacturing and distribution of counterfeit tablets, especially in developing countries, is an urgent and increasingly critical global problem. Falsified medicinal products may contain incorrect ingredients and doses. One of the reasons for drug counterfeiting is the imperfect supply chain system in the pharmaceutical industry. Medicinal products are moved between manufacturers, suppliers, wholesalers, retailers, and pharmaceutical firms before meeting consumers. This study proposes PharmChain, a scenario-oriented drug traceability and regulation blockchain framework that reconstructs the entire service infrastructure by splitting the service provider into three separate service components and ensuring the authenticity and privacy of traceability details. PharmChain can track medication development via patient supply in the pharmaceutical industry. An Ethereum-based blockchain stores the transactions, and only trusted parties can access the data through the chain. We create and test our smart contract code in the Remix environment. We present detailed cost and security analyses incurred by supply chain stakeholders. We also use cost analysis to assess the performance of the proposed solution and demonstrate its affordability. • Introduce PharmChain, a data-driven scenario-based drug traceability and regulation blockchain framework. • Ensure authenticity and privacy of traceability data, enhancing security. • Validate smart contract code rigorously in the Remix environment. • Show the feasibility and affordability of PharmChain through detailed analytics. • Alleviate counterfeit tablet distribution, which poses a pressing and escalating global challenge.

Manjula K. Pawar, Prakashgoud Patil, P. S. Hiremath

Blockchain technology is a nascent technology that possesses attributes such as immutability, security, transparency, openness, and decentralization. It is widely used in industry and business applications. Though it has the best features, it still suffers from some main characteristics, such as scalability and privacy. Scalability is measured through throughput (transactions per second), space, cost, and latency. Bitcoin and Ethereum, which are prominent blockchain platforms, carry out 7 and 20 transactions per second, respectively. This is much less than popular platforms such as VISA, PayPal, and Amazon, which perform thousands of transactions per second. Therefore, this article presents comprehensive study of scalability improving techniques for blockchain and case studies for improving scalability by using some of the techniques. The scalability of blockchain systems can be enhanced by on-chain, off-chain, and machine learning algorithms. The proposed methodology improves the scalability using off-chain technique for supply chain management and KNN classification for the healthcare domain.

Adnan Sagheer, Ali Raza, Muhammad Rizwan Rashid Rana, Faiza Kiran

The highly stochastic, nonlinear, and volatile nature of Bitcoin prices poses significant challenges for accurate forecasting using traditional statistical models. To address this, we propose a hybrid deep learning architecture that combines the strengths of Convolutional Neural Networks (CNNs) for spatial feature extraction with Recurrent Neural Networks (RNNs), specifically Long Short-Term Memory (LSTM) and Gated Recurrent Units (GRU), for capturing long-term temporal dependencies. This integrated framework effectively models both spatial and temporal patterns from historical Bitcoin price data. The model was trained and evaluated using real-world Bitcoin datasets.Experimental results demonstrate that the proposed CNN+LSTM model outperforms traditional machine learning and standalone deep learning approaches. Specifically, it achieves a Root Mean Square Error (RMSE) of 245.76, a Mean Absolute Error (MAE) of 11.45, a Mean Absolute Percentage Error (MAPE) of 15.68%, an R² score of 0.92, and a Mean Bias Error (MBE) of 6.94. These results highlight the effectiveness and reliability of the proposed hybrid model in enhancing the accuracy and stability of financial time series forecasting, providing valuable insights for traders, investors, and financial analysts.

Sina Ahmadi, Maral Mazjini

This chapter explores the transformative potential of generative artificial intelligence (AI) in combating financial fraud, redefining traditional detection systems. It examines generative AI's capabilities in anomaly detection, behavioral modeling, and predictive analytics, addressing fraud complexities from technologies like cryptocurrencies, decentralized finance (DeFi), and AI-driven scams. The integration of generative AI with blockchain enhances transparency, scalability, and proactive prevention. Real-world case studies highlight its effectiveness against credit card fraud, deepfake impersonations, and synthetic identity fraud. Ethical and operational concerns, including AI bias, privacy, and security, are discussed alongside strategies for ethical governance and collaboration. Generative AI is positioned as a key tool for building resilient and trustworthy financial ecosystems to counter current and emerging fraud threats.

Yu Zhang, Yafei Li, Jufang Zhang, Claudio J. Tessone

When analyzing the balance distribution of Bitcoin users, we found that it follows a log-normal pattern based on a rigorous Uniformly-Most-Powerful-Unbiased test. Drawing parallels from the successful application of Gibrat’s law in explaining city size and word frequency distributions, we tested whether a similar principle could account for the log-normal distribution in Bitcoin balances. However, our calculations revealed that the exponent parameters in both the drift and variance terms deviate slightly from 1 when applying Geometric-Brownian-Motion on the Bitcoin balance, which means that Bitcoin users’ balance distribution cannot be explained only by the proportional growth rule alone. During this exploration, Bitcoin users’ behaviors are also investigated. We discovered an intriguing phenomenon: Bitcoin users tend to fall into two distinct categories based on their transaction behavior, which we refer to as “poor” and “wealthy” users. Poor users who initially purchase only a small amount of Bitcoin tend to buy more Bitcoins first and then sell out all their holdings over time. The certainty of selling all their coins is higher and higher with time. In contrast, wealthy users who acquire a large amount of Bitcoin from the start tend to sell off their holdings over time. The speed at which they sell their Bitcoins is lower and lower over time. The wealthier the user, the larger the proportion of their balance and the higher the certainty they tend to sell their holdings. This research provided a new perspective to explore Bitcoin users’ behaviors which may apply to other finance markets.

Shyama Gaur, Harshit Singh, Riju Chaudhary

No abstract is available for this record.

Karthika Veeramani, Suresh Jaganathan, Venkatavara Prasad D

Attendance systems that exist currently are time consuming and vulnerable to modification.The attendance system proposed here is efficient and immutable, using facial recognition for marking and blockchain technology (BT) to secure attendance data.Though facial recognition for marking attendance has overtaken other biometric methods for its convenience, the program to mark attendance is not free from modification by some third party.The novel idea of using permissioned blockchain technology as the solution helps create an immutable privately-owned ledger in a distributed manner for storing attendance data where the code to automate the process of the attendance system is also immutable.

Trishie Sharma, Sandeep K. Shukla

Amid the surge of Non-Fungible Tokens (NFTs) in blockchain, this study introduces a meticulous methodology focusing on transaction behaviors to unveil rug pulls — a critical issue impacting financial security and trust in the NFT landscape. Using a Graph Isomorphism Network (GIN) model with 6 behavioral patterns obtained from transaction sequences, we create a “Rug Pull Pattern Matcher” model. We provide a comprehensive analysis by applying the model on two datasets — creator’s transactions from 50 reputable NFT projects and 32 reported rug pulls. Our work utilizes automated labeling to categorize addresses and our analysis reveals several interconnected NFT creator activities. We present an in-depth mapping of fund flows and creator interactions exposing suspicious behaviors like artificial inflation and intricate network collaborations among creators. The results of our proposed model demonstrate the efficacy of our methodology with 75.4% accuracy and 85.9% precision on the dataset of reported rug pulls. This work provides comparative analyses of genuine and malicious creator networks to elucidate their structural differences, helping to identify genuine and potentially fraudulent NFT activities.