This research explores the application of an Attention-based GRU model for predicting Bitcoin price movements. Historical data from Yahoo Finance, along with technical indicators such as the Stochastic Oscillator (KD index), Relative Strength Index (RSI), and Moving Average Convergence Divergence (MACD), were used to enhance prediction accuracy. The model was designed to focus on key time-series patterns, with the attention mechanism improving its ability to capture crucial market signals. Results show that incorporating these indicators improved performance, with the MACD-enhanced GRU model achieving an accuracy of 75%. The model's effectiveness in volatile cryptocurrency markets highlights the advantages of deep learning models, combined with technical indicators, for accurate financial forecasting.
Jan 16, 2025·2025 International Conference on Cognitive Computing in Engineering, Communications, Sciences and Biomedical Health Informatics (IC3ECSBHI)
There is a growing mobile traffic projected to reach 5016 Exabyte/month by 2030, which explains the rising need for mobile base stations, hence the need for expanding the 5G networks. However, the configuration management of Radio Access Networks (RAN) presents substantial challenges, aggravated by manual processes and multi-stakeholder involvement, which complicates efficient collaboration. This paper advocates for the integration of the smart contract Blockchain technology into network management systems (NMS) to streamline configuration processes, enhance automation, and improve stakeholder transparency and trust. Smart contracts themselves are a code consisting of executed agreements, and therefore NMS can leverage its self-executing features to reduce potential problems while easing network changes along with maintaining immutable transaction records. The system is equipped with some pre-defined concepts and sequences of the events that allow the network elements to change status in accordance with the rules, scenarios, and logic embedded in smart contracts. The framework is aimed at improving effectiveness and efficiency in operating and collaborating within the scope of multiple complex network environments.
Senior Software Engineering Manager in Payments, The Huntington National Bank, Columbus, Ohio, USA, Pushpalika Chatterjee
Background: The rapid evolution of technology in the financial technology (fintech) sector has necessitated the adoption of innovative solutions to address increasing demands for higher data rates, lower latency, and enhanced security. Traditional centralized systems are susceptible to data tampering, service disruptions, and man-in-the-middle attacks, compromising the integrity of sensitive financial transactions. Objectives: This paper aims to explore the convergence of blockchain technology, smart contracts, and machine learning to address security, transparency, and operational efficiency challenges in the fintech sector. It investigates the implications of these technologies for compliance, regulatory frameworks, and ethical governance. Method: The study reviews existing literature and data sources spanning the last decade, with a focus on blockchain applications in fintech. Inclusion criteria include studies on decentralized ledgers, smart contract automation, and machine learning algorithms for predictive analytics. Comparative analyses are presented through flowcharts, graphs, and tables to highlight operational improvements, security enhancements, and cost reductions. Findings: Blockchain technology provides a decentralized and immutable ledger that enhances transparency and security in financial transactions. Smart contracts automate processes, reducing operational costs and improving accessibility to underserved populations. Machine learning enhances blockchain applications by enabling predictive analytics and data-driven decision-making. Despite significant advancements, challenges remain, including the need for robust governance structures to ensure ethical implementation and compliance with regulatory standards. Significance: This review offers new insights by integrating blockchain and machine learning in the context of fintech, addressing critical aspects such as operational efficiency, security, and regulatory compliance that were underexplored in prior studies. It highlights the transformative potential of these technologies in fostering innovation while providing a roadmap for overcoming bottlenecks and paving the way for a secure, inclusive, and efficient financial ecosystem. Keywords: Fintech, AI in Finance, Smart Contracts, Distributed Ledgers, Blockchain
This paper proposes a supply chain transparency improvement and smart contract optimization method based on blockchain, artificial intelligence and communication network. First, combining the decentralized characteristics of blockchain, a transparent and tamper-proof data management platform is designed to automatically execute supply chain transactions through smart contracts, and at the same time, the efficient data transmission characteristics of the communication network are used to achieve rapid synchronization of information between multiple nodes. Secondly, machine learning and deep learning algorithms are used to optimize demand forecasting, resource scheduling and smart contract terms in the supply chain, and real-time data collection and transmission are achieved through the communication network, further improving the overall operation efficiency of the supply chain. Experimental simulation results show that the supply chain system based on this method has significant advantages in improving transparency, the execution efficiency of smart contracts is improved by 30%, and the overall response time is shortened by 20%.
The modern concept of taxation has been accelerated by the emergence of internet-based economy and the use of cryptocurrencies. This shift raises various difficulties for tax authorities in terms of revenue estimates; it requires sophisticated methods for quantitative analysis of intricate economic trends. Previous works have mainly employed conventional ML methods which are weak in their ability to recognize dependencies in the features for data with high dimensionality, hence poor forecast precision. To counter these drawbacks, the use of CapsNets with CNNs, which forms a combined model contributing to better predictive capability is introduced. CapsNets ability to keep ownership of spatial hierarchies and sophisticated features of the input makes the method to accurately extract and analyze features from digital transaction data. Working in Python, the suggested model was compared to several traditional algorithms with which it demonstrated the highest accuracy rate at 99.1%. As concluded from the evaluation, the CapsNet-CNN model is not only resistant to the formulation of new structures, but also flexible to the fluidity of the digital economy environment. This work demonstates the promise of using modern DL methodologies for improving the accuracy of the tax revenues and provides insights for the policy makers who are keen on evoking sensitive and dynamic response strategies of the taxation authorities in a world where more and more of the economic operations are being carried out in the cyberspace. Future research will quantify the components in the model and expand the investigation to other industries and locations.
This study compares the effectiveness of the ARIMA and GRU models in predicting Bitcoin price movements, addressing the need for reliable predictive tools amidst the high volatility of the cryptocurrency market. Previous research has highlighted the strengths of each model in financial forecasting: ARIMA for short-term, stationary data and GRU for capturing complex temporal patterns. The purpose of this study is to evaluate which model performs better in the context of Bitcoin price prediction, offering insights for investors to minimize risks and enhance decision-making in this unpredictable market. The research methodology involves applying both models to Bitcoin price data and comparing their accuracy using the Mean Absolute Percentage Error (MAPE) across various forecasting intervals. Results indicate that GRU achieves higher accuracy in long-term forecasts, while ARIMA performs optimally for shorter time frames. However, both models demonstrate limitations, especially as the prediction horizon extends, underscoring the inherent challenges of cryptocurrency price forecasting. These findings suggest that GRU may be better suited for longer investment horizons, while ARIMA remains effective for short-term predictions. The conclusions affirm the potential of using these models selectively to align with specific investment strategies in cryptocurrency markets, although further research is recommended to improve predictive accuracy under evolving market conditions.
This paper discusses the use of Artificial Intelligence (AI) to enhance workplace productivity and employee well-being. By integrating machine learning (ML) techniques with neurobiological data, the proposed approaches ensure alignment with human ethical standards through value alignment models and Hierarchical Reinforcement Learning (HRL) for autonomous task management. The system utilizes biometric feedback from employees to generate personalized health prompts, fostering a supportive work environment that encourages physical activity. Additionally, we explore decentralized multi-agent systems for improved collaboration and decision-making frameworks that enhance transparency. Various approaches using ML techniques in conjunction with AI implementations are discussed. Together, these innovations aim to create a more productive and health-conscious workplace. These outcomes assist HR management and organizations in launching more rational career progression streams for employees and facilitating organizational transformation.
In the era of emerging technologies, many firms explore the role of blockchain technology and its business value impact. Research on firm value has shown that companies benefit from executing blockchain projects, but little is known about specific value drivers. Theoretically founded, we demonstrate under which conditions blockchain provides additional firm value. Utilising the event study methodology, we examine investors' reactions to companies announcing blockchain initiatives and apply the theoretical lens of signaling to explain factors that lead to positive stock market reactions. Based on an international sample of 606 blockchain announcements, our study shows that stock markets react more positively to blockchain projects if the project has been successfully finished, relates to the company's business processes, or is announced by firms based in the USA. Moreover, announcements during blockchain and cryptocurrency hypes lead to higher stock market returns.
Blockchain technology (BCT) has emerged as a promising solution for ensuring supply chain traceability. However, not all consumers have a comprehensive understanding of the benefits associated with BCT-enabled traceability. In this article, we investigate the impacts of consumer awareness on the adoption of BCT within a supply chain comprising a manufacturer and a retailer. We develop two distinct scenarios: Scenario B, where the supply chain traceability is managed via traditional digital systems, and Scenario E, where the supply chain traceability is managed via BCT-enabled systems. We introduce the concept of consumer traceability awareness level, representing the proportion of the consumer population that is knowledgeable about the advantages of these traceability technologies. The findings reveal that the adoption of BCT enhances the overall performance of the supply chain and makes it more sensitive to the consumer traceability awareness level. Nonetheless, the manufacturer consistently experiences advantages from BCT adoption, whereas the retailer's situation may deteriorate. In both scenarios, a low traceability awareness level prompts the retailer to target all consumers, whereas a high-traceability awareness level shifts its focus solely to the knowledgeable consumers. Intriguingly, the adoption of BCT shifts the retailer's inclination toward targeting the knowledgeable consumers rather than all consumers.
Samer Mohammed Fakhri Darar, Giasuddin Ahmed, Hanan Mohammed Ibrahim
The research aims to identify the influencing macroeconomic factors in Bitcoin and an attempt to explain the reasons for the sharp fluctuations in this currency. The research used the inductive approach as well as the standard method through comparison between Standard methods Approved and including (OLS, ARDL) which means trying to detect N Some spurious relationships between the studied variables. The research reached to There is a direct relationship between changes in the global gold price and the Bitcoin price, and an inverse relationship between the federal interest rate and the Bitcoin price, as well as a direct relationship between Economic shocks and Price changes a job And Bitcoin, and the research presents some proposals to address the sharp fluctuations in Bitcoin prices, including holding an international conference focusing on examining the causes of these fluctuations and ways to reduce their serious effects on investment portfolios. For individuals and financial institutions.
In today's digital world, online transactions are an everyday occurrence.From shopping and sending money to sharing information, these digital exchanges provide convenience but also come with significant risks.Ensuring the safety of these transactions is crucial, as a single security breach can lead to substantial financial losses and erode trust in the system.Blockchain technology presents a promising solutionby decentralizing control, making it much harder for hackers to manipulate the data.This paper explores how blockchain protects digital transactions, the challenges it faces, and its potential to transform various industries, such as finance and healthcare.Understanding blockchain security helps us appreciate its role in fostering trust and transparency in our online activities, ultimately making digital interactions safer for everyone involved.
In today's financial landscape, individuals face challenges when it comes to determining the most effective investment strategies. Cryptocurrencies have emerged as a recent and enticing option for investment. This paper focuses on forecasting the price of Ethereum using two distinct methods: artificial intelligence (AI)-based methods like Genetic Algorithms (GA), and econometric models such as regression analysis and time series models. The study incorporates economic indicators such as Crude Oil Prices and the Federal Funds Effective Rate, as well as global indices like the Dow Jones Industrial Average and Standard and Poor's 500, as input variables for prediction. To achieve accurate predictions for Ethereum's price one day ahead, we develop a hybrid algorithm combining Genetic Algorithms (GA) and Artificial Neural Networks (ANN). Furthermore, regression analysis serves as an additional prediction tool. Additionally, we employ the Autoregressive Moving Average (ARMA) model to assess the relationships between variables (dependent and independent variables). To evaluate the performance of our chosen methods, we utilize daily historical data encompassing economic and global indices from the beginning of 2019 until the end of 2021. The results demonstrate the superiority of AI-based approaches over econometric methods in terms of predictability, as evidenced by lower loss functions and increased accuracy. Moreover, our findings suggest that the AI approach enhances computational speed while maintaining accuracy and minimizing errors.
As crypto exchanges and decentralized exchanges have proven untrustworthy, this paper seeks to create a rigorous Blockchain Project Evaluation Model (BPEM) for assessing the trustworthiness of a blockchain project. This BPEM will collate the components of technical audit, on-chain and off-chain analytics, liquidity indicators, and behavioral indicators into a single score of the project. The relevance of this work is driven by widespread instances of trade volume manipulation, opaque tokenomics, and tightening regulatory requirements (including in the context of MiCA). The scientific novelty lies in the creation of a hybrid MCDM architecture with an automated Incongruity Detection System (IDS) module that cross-checks tokenomics, liquidity, on-chain activity, and public statements and introduces a penalty coefficient into the final rating. The results of BPEM validation across case studies of wash trading and hidden centralization demonstrate that the key indicators of project resilience are not nominal volume but market depth, liquidity quality, and the integrity of on-chain data, and that identified inconsistencies act as early markers of scam projects and systemic risks. It is shown that a comprehensive multifactor analysis significantly outperforms the use of isolated metrics and can serve as a backbone for listing and compliance procedures. The article is of practical value for researchers of decentralized finance, risk managers, crypto exchange analysts, and digital asset regulators.
The rise of digital payments enhances global internet and mobile usage. However, there are still issues with customer satisfaction in mobile e-banking. This study examines how mobile banking service quality impacts customer satisfaction, detects hackers, and offers solutions for improvement through blockchain integration. This study compares artificial neural network performance with ML models like naive Bayes and XGBoost. The validated data is first sent to cloud for verification, and then securely stored on blockchain to protect customer information. The study uses ANN, a DL model to reduce hacking and ensure secure transactions for enhanced security. The proposed approach is implemented using Python platform and Ethereum tool. The study shows that the ANN model outperforms the ML models in terms of security, achieving an accuracy rate of 99.44%, making the proposed model ideal for e-banking applications. This approach not only enhances security against hacking but also builds customer trust and satisfaction.
Jan 1, 2025·Konference doktorandů na Vysoké škole finanční a správní 2025: Prezentace výsledků společenskovědního výzkumu s ekonomickými a finančními efekty (12. ročník) = Doctoral Student Conference at the University of Finance and Administration 2025: Results presentation of social science research with economic and financial effects (12th annual conference)
Cieľom príspevku je analyzovať rozdiely vo faktoroch, ktoré ovplyvňujú správanie kryptomeny Bitcoin (BTC/USD) v porovnaní s tradičným menovým párom euro/dolár (EUR/USD). Využívame viacnásobnú regresnú analýzu na identifikáciu makroekonomických a trhových determinantov, ktoré pôsobia na vývoj týchto aktív. Výsledky ukazujú, že hodnota BTC/USD je ovplyvňovaná najmä volatilitou akciového trhu a objemom transakcií v sieti Bitcoin, zatiaľ čo vývoj EUR/USD je podmienený predovšetkým zmenami dolárového indexu a úrokového diferenciálu. Zistenia podporujú hypotézu, že Bitcoin má potenciál správať sa ako alternatívna trieda aktív na globálnych finančných trhoch, avšak jeho správanie sa stále výrazne líši od tradičných mien.
Blockchain technology and cryptocurrencies are reshaping traditional financial systems by introducing decentralized, transparent, and efficient alternatives.This research paper examines the transformative role of blockchain in banking and finance, focusing on applications such as cross-border payments, decentralized finance (DeFi), smart contracts, and central bank digital currencies (CBDCs).It evaluates the opportunities for innovation, including cost reduction, enhanced security, and financial inclusion, while addressing critical challenges such as regulatory uncertainty, scalability limitations, and environmental concerns.Through case studies of institutional adoption (e.g., JPMorgan's JPM Coin) and national strategies (e.g., El Salvador's Bitcoin adoption), the paper highlights both successes and pitfalls.The analysis concludes with recommendations for harmonized global regulations, infrastructure investment, and balanced risk management to foster sustainable integration of blockchain into mainstream finance.This study synthesizes academic research, industry reports, and real-world implementations to provide a comprehensive overview of crypto and blockchain's evolving impact on financial ecosystems.
Cryptocurrencies are rapidly emerging as a novel virtual financial system with significant implications across various industries. This study systematically reviews the factors influencing cryptocurrency adoption, identifying key motivators and barriers that affect individuals’ decisions to embrace this technology. Our findings reveal that while there is increasing interest in cryptocurrencies, substantial gaps remain in understanding the underlying motivations for adoption and the disparities in acceptance across different regions. We categorize these gaps and propose future research directions aimed at bridging them. Ultimately, this review contributes to a deeper understanding of cryptocurrency adoption dynamics and highlights the need for more comprehensive studies in this evolving field.