Abstract A Non-Fungible Token (NFT) is a digital asset representing ownership or proof of authenticity of a unique digital item. NFTs are used for various purposes, including digital art, collectibles, virtual real estate, and tokenizing unique digital or physical items, and have introduced new dimensions to digital ownership and enabled individuals to tokenize unique digital assets using blockchain technology. Although NFTs offer exciting opportunities, they suffer from interoperability, high energy consumption, piracy, ownership control, and security issues. In this paper, an idea has been proposed in which any image, pdf file, or video file can be converted to an NFT and owned. We have used the ERC-721 standards, the PoS consensus protocol, and a smart contract to address the challenges. The proposed framework provides a step-by-step guide to create, list NFTs and maintain secure ownership where metadata are stored on IPFS, which generates a unique URL. This URL is then logged on the blockchain, saving time and costs. The created NFTs are interoperable among various applications and frameworks. Smart contract has been formally verified using Slither and tested against vulnerability using Smart Contract Weakness Classification (SWC) standards. Performance of the proposed system has been measured in terms of execution cost, latency, and throughput including statistical indicators like variance and confidence intervals. Minting cost has been compared with the similar network condition.
Open access
Blockchain Technology Applications and Security
Advanced Steganography and Watermarking Techniques
D. A. Vidhate, Prajesh Gaikwad, Aditya Gadge, Abhijay Jadhav · 5 authors
The growth of financial technology has introduced Central Bank Digital Currency (CBDC), which is basically a digital version of money issued by central banks. In this work, a blockchain-based system is proposed that uses QR codes and UID numbers to make transactions easier and more secure. Blockchain helps keep a proper record of transactions so they cannot be easily changed or tampered with. Using QR codes makes payments quick and simple, especially for everyday use. The system also uses smart contracts to handle processes automatically. Since everything runs on a decentralized network, it reduces dependency on a single authority and lowers the chances of fraud. At the same time, user privacy is maintained by storing only encrypted verification data instead of actual personal details.
Bobba Pavan Santosh, Bommeneni Pavan Madhav, Dr. J. R. Jayavelu, Dr. P. Dhivya
Cryptocurrencies have found their way into contemporary financial systems as a significant component of modern-day financial systems because of their decentralized nature, their ease of adoption and uptake. Ether is considered to be one of the most actively traded currencies and its value tends to be highly volatile. It is not easy to forecast the market price trend of Ethereum due to the influence that technical trends, investor behavior, and external factors have over the market. In this project, the researcher will use machine learning to assess the future price direction of Ethereum the following day through the use of Python. The past trends of prices are analyzed and augmented with various technical indicators in order to reflect the market trends and momentum. The best potential machine learning model was selected after training and evaluating many models using Logistic Regression. The results demonstrate that machine learning may be used to provide rational insights into the price movement of Ethereum and to aid in decision-making using these insights.
Ammar Ahmed Othman, Seddiq Hassan Al-Banna Ali, Mohammed Bakr Youssef
In the digital currency, Bitcoin (BTC) is called the gold of the digital currency. It is possible to make some profits in trading of bitcoins, though this market is a very illiquid market and it is very challenging to determine the price of a bitcoin. The current work uses historical data and technical indicators to predict Bitcoin prices in a broad approach. BTC-USD price data were obtained using Yahoo Finance API and covered from 01/01/2015 till 07/01/2024. The concept of feature engineering was applied to improve the dataset by including vital financial characteristics, including Moving Averages, RSI, and Bollinger Bands for higher forecasting precision. The forward-looking model for the Bitcoin price was developed using machine learning and deep learning algorithms. The efficiency of the model was assessed with the help of Mean Absolute Error (MAE), Mean Squared Error (MSE), and Root Mean Squared Error (RMSE). The overall values of Mean Absolute Error, Mean Squared Error, and Root Mean Squared Error were 0.0062, 8.39e-05 and 0.0092 respectively which suggest that the proposed model is accurate in forecasting the future prices.
Deep learning has emerged as a widely applied approach across various fields, with finance and forecasting being among its most prominent areas of use. Within this domain, different deep learning architectures have been developed to address specific prediction problems. This study compares the performance of ARIMAX and several deep learning models—including LSTM, BILSTM, CNN-LSTM, GRU, and TFT—in forecasting Bitcoin prices. The dataset consists of daily values from January 2014 to January 2025. The dependent variable is the daily Bitcoin closing price ($), while the independent variables include oil price (USD/barrel), gold price (USD/ounce), platinum price ($/XPT), and the USD/TRY exchange rate. All analyses were conducted in Python using Google Colab, with the Keras library employed for model implementation. Root Mean Square Error (RMSE) was selected as the evaluation metric for predictive accuracy. The results indicate that the TFT model achieved the highest predictive performance, followed closely by the GRU model. LSTM, BILSTM, and ARIMAX models showed similar yet weaker performance, while the CNN-LSTM model produced the least accurate forecasts, with significantly higher RMSE values compared to the other models.
In the rapidly evolving landscape of cryptocurrency in India, a powerful new contender has emerged—Jaimax Coin, often hailed as the best presale crypto coin in India. As blockchain technology reshapes finance, digital ownership, and decentralized ecosystems, we stand at the forefront of innovation, introducing Jaimax, the next-generation crypto pre-sale coin designed for long-term scalability, high utility, and mass adoption. As a revolutionary new crypto coin India trusts for transparent and secure financial growth, Jaimax is strategically engineered to transform both the DeFi (Decentralized Finance) and NFT (Non-Fungible Token) markets. With advanced tokenomics, unmatched security standards, and a visionary roadmap, Jaimax is positioned to become one of the most influential digital assets in India’s expanding blockchain environment.
In India’s rapidly expanding digital finance ecosystem, Jaimax Coin has emerged as one of the most reliable, transparent, and growth-oriented blockchain assets. As the demand for secure crypto coin options increases, Jaimax is positioned as one of the best presale crypto coin in India, offering visionary investors unmatched opportunities in the evolving world of decentralized finance, NFTs, and digital currency innovation. Backed by advanced blockchain architecture, transparent tokenomics, and a strong mission toward accessible financial technology, Jaimax stands apart from the countless new crypto coins in India.
Rashed Alnuman, Tayyab Sajid, Wesam Almobaideen, Qusai Hasan
Abstract Blockchain technology has revolutionized digital financial transactions and asset ownership by enabling decentralized and automated operations through smart contracts. Solidity smart contracts, used in the Ethereum blockchain network, facilitate secure and trustless execution of agreements. However, like any code, smart contracts are prone to vulnerabilities. Considering the assets and value of currency these smart contracts handle, their exploitation leads to severe financial losses and loss of operations. Such exploits have resulted in billions of dollars in stolen or locked assets. In this paper, we present an ensemble multilabel classifier model approach for the automated detection of vulnerabilities in Solidity smart contracts using a real smart contract dataset, with a detailed methodological process that includes processing the dataset. The proposed model stack achieves excellent results with F1 scores ranging from 82.0% to 99.9% for each vulnerability dataset. The proposed model is also compared with common static analyzer tools and models proposed in the literature following a similar approach. Moreover, we package the models into a web application, demonstrating deployment and functionality.
Lingling Xia, Tao Zhu, Zhengjun Jing, Qun Wang · 7 authors
Digital currencies, led by Bitcoin and USDT, are characterized by decentralization and anonymity, which obscure the identities of traders and create a conducive environment for illicit activities such as drug trafficking, money laundering, cyber fraud, and terrorism financing. Focusing on the USDT-TRC20 token on the Tron blockchain, we propose a two-layer transaction network-based approach for virtual currency address identity recognition for digging out hidden relationships and encrypted assets. Specifically, a two-layer transaction network is constructed: Layer A describes the flow of USDT-TRC20 between on-chain addresses over time, while Layer B represents the flow of TRX between on-chain addresses over time. Subsequently, an identity metric is proposed to determine whether a pair of addresses belongs to the same user or group. Furthermore, transaction records are systematically acquired through blockchain explorers, and the efficacy of the proposed recognition method is empirically validated using dataset from the Key Laboratory of Digital Forensics. Finally, the transaction topology is visualized using Neo4j, providing a comprehensive and intuitive representation of the traced transaction pathways.
Samsudin Samsudin, Muhammad Dedi Irawan, Muhammad Irwan Padli Nasution, Raissa Amanda Putri
Bitcoin’s extreme price volatility has long posed challenges for both investors and researchers seeking reliable forecasting models. Conventional financial approaches often fail to capture the highly complex, nonlinear, and fast-moving nature of cryptocurrency markets. To address this gap, this study develops a Bitcoin price prediction model using Random Forest Regression based on on-chain market data. The dataset was obtained from publicly available historical Bitcoin daily trading records spanning more than five years. Key features include opening price, daily high and low ranges, trading volume, and percentage change. The research was carried out in several stages. First, data preprocessing was conducted through normalization, handling of missing values, and feature engineering. Second, model training was performed with Random Forest, including parameter tuning to optimize predictive accuracy. Third, model evaluation employed R² and Mean Absolute Percentage Error (MAPE) as primary performance indicators. Fourth, visualization was implemented using interactive charts to allow users to observe short-term price fluctuations and long-term market patterns. The system development followed an iterative methodology inspired by the Streamlit Framework, which is an open-source Python library that simplifies building interactive web applications for data science and machine learning. This approach provides flexibility, enabling rapid experimentation and adaptation to evolving market conditions. The results show that the proposed model achieves near-perfect R² values (approaching 1.0) with consistently low MAPE, highlighting its reliability. Beyond predictive performance, the framework is designed to be scalable, supporting future integration with deep learning methods such as LSTM and external macroeconomic indicators, thus offering both practical utility for investors and academic contributions to decentralized finance research.
Muhammad Haroon Tariq, Uswa Ihsan, Zaenal Alamsyah
Ownership rights related to land and property represent a highly contentious matter in areas across Pakistan because female inheritors struggle to assert their property rights due to cultural practices along with unclear procedures and traditional document systems. The present government-controlled systems demonstrate inadequate proficiency along with safety protocols to execute fair inheritance distribution, mainly impacting marginalized populations. This research introduces a blockchain system known as the Land Registration and Inheritance Automation System (LRIAS) which prioritizes the female protection of inheritance privileges. The proposed system includes digitalizing the traditional paper-based land registration and inheritance process. The system ensures blockchain security through the implementation of MetaMask together with Web3.js for Ethereum transactions. The blockchain system distributes inheritances through programmed agreements which follow Shariah validation rules. The LRIAS establishes permanent and free-version records that show who owns land and who the legal heirs are. The system enables women to access their inheritance records through verifiable reliable data which cannot be altered. Through the system, authorities can verify inheritance claims and execute them without bureaucratic interference, which minimizes both legal disputes and family conflicts. Experimental tests show that the LRIAS succeeds in safeguarding women’s land inheritance claims and increasing confidence in legal inheritance procedures.
Hakam Dzakwan Diash, Vannesa Nathania, Mohammad Idhom, Trimono Trimono
The volatile and dynamic Ethereum (ETH) market demands an accurate predictive model to support investment decision making. The complexity of ETH time series data and the influence of various external factors make price prediction a challenge in itself. This study aims to develop an ETH price prediction model using a combined architecture of Convolutional Neural Network (CNN) and also Bidirectional Long Short-Term Memory (BiLSTM). CNN is used to extract local features from historical ETH closing price data, while BiLSTM models bidirectional temporal patterns. The dataset used includes ETH daily price from January 2020 to January 2025, which are obtained from Yahoo Finance and have gone through a normalization process and transformation into sequential form. The model is trained for 100 epochs with an early stopping mechanism to prevent overfitting and evaluated using the MAPE and coefficient of determination (R²) metrics. The evaluation results show that the CNN-BiLSTM model is able to predict ETH prices with a MAPE value of 2.8546% and an R² of 0.9415, indicating high performance in capturing actual data trends. This study shows that the hybrid CNN-BiLSTM approach is effective for Ethereum price prediction.
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.
Halilibrahim Gökgöz, Aamir Aijaz Syed, Hind Alnafisah, Ahmed Jeribi
The recent economic turmoil and the increasing volatility of bitcoins have necessitated the need for exploring safe-haven assets for bitcoins. In this quest, the present study aims to investigate the safe haven for bitcoins by examining the dynamic relationship between bitcoins, gold, foreign exchange, and stablecoins. This is achieved by calculating hedge ratios and portfolio weight ratios for various asset classes, by employing adaptive-based techniques such as generalized orthogonal generalized autoregressive conditional heteroscedasticity, corrected dynamic conditional correlation, corrected asymmetric dynamic conditional correlation, and asymmetric dynamic conditional correlation under various market and time-varying conditions. The empirical estimate reveals that all the selected asset classes are effective risk diversifiers for bitcoins. However, among all the asset classes, as per the hedge and portfolio weight ratio, Japanese yen, stablecoin for Japanese yen and Great Britain Pound, and Crypto Holding Frank Token (lowest-cost hedging strategies) are the most effective risk diversifiers when compared with bitcoins. Moreover, while considering external economic shocks, the empirical estimate posits that stablecoins are more stable risk diversifiers compared to the asset class they represent. Furthermore, in terms of the bivariate portfolio analysis formed with bitcoin, this study concludes that the weight of bitcoin is more stable when combined with gold, tether gold, Euro, Great Britain Pound, Swiss franc, and Japanese Yen. Thus, these assets are attractive for long-term investment strategies. This study provides investors and policymakers with significant insight into understanding safe-haven assets for bitcoin’s volatility and constructing a flexible portfolio that is dependent on the investment timeline and the prevailing market conditions.
The article examines methods and information technologies aimed at ensuring the secure integration of the Ethereum blockchain with Internet of Things (IoT) systems. The relevance of the study is driven by the rapid development of IoT, which is accompanied by increasing cybersecurity threats, including unauthorized data access, man-in-the-middle (MITM) attacks, device identifier spoofing, and the low transparency of centralized systems. The use of Ethereum blockchain technology, particularly smart contracts, opens new opportunities for creating decentralized security management models for IoT devices, enhancing trust levels, automating processes, and minimizing third-party interference risks. The “Problem statement” section outlines the key challenges in securing IoT networks, including the vulnerabilities of centralized solutions, limited computational resources of devices, and the need to develop autonomous access control systems. The “Analysis of Recent Research and Publications” section summarizes modern approaches to integrating Ethereum blockchain into the IoT field, including tokenized identification mechanisms, access control, and transaction processing using smart contracts. It is noted that leading researchers suggest Layer-2 solutions (state channels, zk-rollups, Plasma) aimed at reducing the load on the main blockchain and improving scalability. The aim of the article is to systematize modern methods of integrating the Ethereum blockchain with IoT and develop recommendations for their implementation, considering the limited resources of devices. The “Research results” section presents a secure IoT system architecture concept based on decentralized account management, local storage of cryptographic keys on devices, the use of optimized transaction signing algorithms, and the introduction of a hybrid data storage model based on IPFS. The proposed model minimizes the risk of unauthorized access, increases transparency in the interaction between IoT devices, and reduces computational resource costs. The “Conclusions and prospects for further research” section emphasizes that the implementation of the Ethereum blockchain in IoT promotes the development of secure decentralized platforms. However, it requires addressing issues such as energy consumption, transaction costs, and optimizing client applications for low-performance devices. Future research should focus on developing effective scalability tools, adapting smart contracts to IoT specifics, and improving integration with cloud computing platforms for storing large data sets.
The integration of blockchain technology within the domain of digital cultural heritage resources (DCHR) has emerged as a pivotal approach over the past decade, offering a secure and transparent platform for documentation, ownership transfer, and verification. This paper investigates the current challenges in managing DCHR and analyzes the corresponding solutions. We discuss outstanding technical implementations such as the “Digital Dunhuang Open Material Library” and “Salsal.” Our study identifies emerging blockchain trends in cultural heritage preservation and proposes future research directions. Through an analytical examination of distributed consensus mechanisms and blockchain deployment scenarios, this study proposes methodological pathways for implementing the DCHR management framework. We call for continued optimization of consensus protocols, expansion of blockchain application scenarios, and establishment of supportive policies to bridge the gap between decentralized innovation and institutional compliance requirements.
Mubarak A. Khan, Md Mofijul Islam, Istiaq Ahmed, Md Masud Karim Rabbi · 10 authors
Peer-to-peer trading and the move to decentralized grids have reshaped the energy markets in the United States. Notwithstanding, such developments lead to new challenges, mainly regarding the safety and authenticity of energy trade. This study aimed to develop and build a secure, intelligent, and efficient energy transaction system for the decentralized US energy market. This research interlinks the technological prowess of blockchain and artificial intelligence (AI) in a novel way to solve long-standing challenges in the distributed energy market, specifically those of security, fraudulent behavior detection, and market reliability. The dataset for this research is comprised of more than 1.2 million anonymized energy transaction records from a simulated peer-to-peer (P2P) energy exchange network emulating real-life blockchain-based American microgrids, including those tested by LO3 Energy and Grid+ Labs. Each record contains detailed fields of transaction identifier, timestamp, energy volume (kWh), transaction type (buy/sell), unit price, prosumer/consumer identifier (hashed for privacy), smart meter readings, geolocation regions, and settlement confirmation status. The dataset also includes system-calculated behavior metrics of transaction rate, variability of energy production, and historical pricing patterns. The system architecture proposed involves the integration of two layers, namely a blockchain layer and artificial intelligence (AI) layer, each playing a unique but complementary function in energy transaction securing and market intelligence improvement. The machine learning models used in this research were specifically chosen for their established high performance in classification tasks, specifically in the identification of energy transaction fraud in decentralized markets. To guarantee the reliability and accuracy of the used machine learning models, an extensive battery of evaluation metrics was utilized. The plot demonstrates clearly that XG-Boost obtained the highest accuracy out of the three models, Random Forest was slightly lower, and conversely, Logistic Regression was the lowest of the three models. Integrating blockchain technology with AI can increase the transparency, security, and efficiency of the energy sector in the U.S. Blockchain's decentralized and immutable ledger can make energy transactions traceable and resistant to tampering, and it becomes extremely hard for malicious actors to manipulate prices or fake records. In the future, the integration of deep learning methodologies and real-time integration of data from the Internet of Things (IoT) holds promising implications for future improvements. Deep learning models like Convolutional Neural Networks (CNNs) and Recurrent Neural Networks (RNNs) can detect strongly nonlinear patterns of fraud, which conventional models may not identify, particularly for the usage of multivariate time-series data from smart meters, sensors, and distributed energy resources.
Bitcoin is the most traded cryptocurrency by volume and market cap. A number of scholars have directed their research towards characterizing Bitcoin’s speculative behavior using a myriad of techniques such as technical analysis, price regression, and direction classification. For this work, research is conducted using the relatively nascent technique of on-chain data analysis. The goal of this research is to evaluate Bitcoin’s on-chain data in predicting future price direction. First, a classification process of on-chain data features that helps the reader understand their relevance is proposed. To address the curse of dimensionality, feature selection algorithms such as L1 regression, Boruta, and the dimensionality reduction algorithm Principal Component Analysis (PCA) are utilized. The research then explores advanced neural networks for next day price direction prediction, including the Convolutional Neural Network-Long-Short Term Memory (CNN-LSTM) and the Temporal Convolutional Network (TCN). Neural network models and trading strategies are then compared based on their return statistics. A comparative analysis of feature selection, learning model performance, and trading strategy performance is also conducted. Results from the research show that the Boruta feature selection algorithm combined with the CNN-LSTM model performs best compared to other combinations with a prediction accuracy of 82.03% over the testing period. In addition, the on-chain features within the category, realized value, and unrealized value classifications have higher predictive powers for next day price direction prediction. Finally, during trade simulations, the CNN-LSTM model with a Long-Short strategy had an annualized return of 1682.7% and a Sharpe Ratio of 6.47.
Cryptocurrency is a new type of asset that has emerged with the advancement of financial technology, creating significant opportunities for research. bitcoin is the most valuable cryptocurrency and holds significant research value. However, due to the significant fluctuations in bitcoin's value in recent years, predicting its value and ensuring the reliability of these predictions, which have become crucial, have gained increasing importance. A method that combines Long Short-term Memory (LSTM) with conformal prediction is proposed in this paper. Initially, the high-dimensional features in the dataset are divided using the Spearman correlation coefficient method, and features below 0.75 and above 0.95 are excluded. Subsequently, an LSTM model is built, and data are fed into it and the data is used to train the model to generate predictions. Finally, the predicted values generated by the LSTM are fed into the conformal prediction model, and confidence intervals for these values are generated to verify their reliability. In the conformal prediction model, the quantile loss of the loss function is defined, and an Average Coverage Interval (ACI) predictor is designed to improve the accuracy of the results. The experiments are conducted using data from CoinGecko, which is a publicly available data. The results show that the LSTM-conformal prediction (LSTM-CP) combination improves reliability.
Dušan Morháč, Kristián Košťál, Viktor Valaštín, Ivan Kotuliak
Abstract Interoperability is a critical aspect of fluent liquidity and healthy blockchain ecosystems. Achieving seamless interoperability within heterogeneous blockchains often proves challenging due to the inconsistencies in architecture, asset registration and management logic, implementations, and smart contract designs. These unresolved challenges frequently cause fragmented liquidity within ecosystems. This paper proposes a modular and novel solution, UniSpell, that works as a universal adapter to achieve seamless interoperability and overcome fragmented liquidity problems. This is possible by leveraging Polkadot’s native cross-chain protocol, XCMP, allowing developers to implement dApps that can source liquidity, cross-chain transfer, and swap assets within one line of code. UniSpell presents a framework that is easily extendable and applicable to multichain ecosystems outside of its native ecosystem, Polkadot. UniSpell’s primary goal is to cultivate a dynamic ecosystem by enhancing liquidity and encouraging the addition of new assets. This approach enables innovation and broadens the adoption of decentralized finance (DeFi) solutions.
Abdullah Ayub Khan, Asif Ali Laghari, Syed Azeem Inam, Sajid Ullah · 6 authors
Rapid technological breakthroughs in recent years, like Deepfake, have made it feasible to produce synthetic media that is remarkably lifelike, but they also present significant hazards to public trust, privacy, and security. This survey paper reviews the latest techniques for detecting deepfakes, focussing on important components as image and video manipulation, audio spoofing, and multimodal synthesis. It features state-of-the-art methods including machine learning (ML), deep learning (DL), and multimodal architectures that are especially made to address the previously described deepfake criteria. The report provides a critical review of assessment measures used to assess detection model performance, including precision, accuracy, recall, computing effectiveness and efficiency, and fast responses to adversarial attacks. In order to assist direct future research, this highlights recent advancements in the subject, including explainable AI, federated learning, and self-supervised learning hierarchy. In order to examine the problems with adversarial attacks, scalability across different datasets, and the ethical implications of detection techniques, it is also vital to look into the technological and societal challenges surrounding multimedia-enabled deepfake detection. In particular, the usage of Blockchain Distributed Ledger Technology (BDLT) for traceability, lightweight modelling, and resilient systems forms for cross-model deepfake evaluation are discussed in this review study along with potential solutions to these limitations and areas for further research. This paper offers a comprehensive resource for future research, experts, and practitioners looking to combat the growing threat of deepfake, especially in the social media space, using innovative and useful detection tools.
Open access
Digital Media Forensic Detection
Generative Adversarial Networks and Image Synthesis
Bitcoin is a decentralised digital currency that has been in existence for some time now. Its value has been volatile, with most of its prices fluctuating significantly, making it difficult to predict its prices when investing. This paper employed a Neural Basis Expansion Analysis Time Serie (N-BEATS) deep learning architecture to predict Bitcoin prices. The model was chosen because of its proven capabilities of modelling intricate patterns in time series data. An hourly Bitcoin price data of 729 days collected from Yahoo Finance extensively assesses the N-BEATS model's performance while comparing it with other machine learning models like the Linear Regression and the long-short-term-memory (LSTM) networks. Mean Absolute Error (MAE) and R-squared (R²) were utilised as performance evaluation metrics. N-BEATS surpassed the others by providing an R² score of 0.00240 and an MAE score of 0.9998. These findings are significant and shed light on how deep learning models can be used for financial forecasting. The result shows that the N-BEATS model is more accurate and reliable for predicting cryptocurrencies' prices, which may be very useful for investors in making decisions and managing risks.
This study evaluates the effectiveness of the CNN-LSTM hybrid model in predicting the Ethereum exchange rate against the United States Dollar (USD) by comparing the performance of the model without optimization and the model with hyperparameter optimization using Bayesian Optimization. The dataset used is sourced from Yahoo Finance covering the period 2017-2023. The results show that the CNN-LSTM model with hyperparameter optimization consistently outperforms the model without optimization, with improved prediction accuracy shown through the RMSE, MAE, MAPE, and R² values. Hyperparameter optimization resulted in an optimal configuration with 166 filters, kernel size 5, 168 LSTM units, 91 dense units, learning rate 0.00114, and batch size 32. This research confirms the effectiveness of the CNN-LSTM hybrid approach in predicting crypto exchange rates, and demonstrates the importance of hyperparameter optimization in improving prediction accuracy.