This research explores the application of machine learning techniques to predict Bitcoin price dynamics. Bitcoin, as a decentralized digital currency, has garnered significant attention due to its high volatility and potential for rapid value fluctuations. This study aims to develop a machine learning model that analyzes historical Bitcoin price data to identify patterns and predict future price trends. While precise short-term predictions may be challenging, the model can provide valuable insights into overall price trends and inform investment strategies. This research contributes to a better understanding of Bitcoin price dynamics and has the potential to assist investors in making more informed decisions.
This study examines the bitcoin price in USD in the world by developing a suitable time series model to identify its future trends. This data set consists of monthly bitcoin prices from August 2010 to July 2024. It was found that the original series is not stationary and not seasonality. The stationary was achieved by the first difference. Of the parsimonious models identified based on the Partial Autocorrelation Function (PACF) and Autocorrelation Function (ACF) of the stationary series, an auto-regressive integrated moving average (ARIMA) (2,1,2) model was identified as the best-fitt ed model. The significance of the model and its parameters and information criteria such as the Akaike Information Criterion (AIC), Schwarz Criterion, and log-likelihood was used to identify the best-fitted model. The model was trained using data from August 2010 to March 2024. The residuals of the model were found to be white noise. The mean absolute percentage error (MAPE) for validation data is 7.09%. The percentage errors for the validating set are all positive and varied from 3.5% to 12.9%. The predicted Bitcoin price (USD) from August to October 2024 are $59947.88, $60308.7, and $60669.53. Bitcoin price can be utilized by market demand and supply, regulatory environment, and technology development. Keywords: ACF; ARIMA models; Bitcoin price; Forecasting; PACF; Time series analysis
The world is witnessing a noticeable increase in financial exchange in digital currencies such as Bitcoin, Ethereum, and others, as transactions in electronic markets have begun to rise recently, which increases the difficulty of maintaining security and trust in decentralized financial systems that use distributed databases and the technologies that interact with them in Ethereum networks, blockchain, etc. This study presents a hybrid model based on the PyCaret library and includes 12 machine learning classifiers, with the aim of identifying fraudulent activities in Bitcoin transactions and enhancing the security of Ethereum networks and blockchain technology. The results reveal the effectiveness of different models in identifying fraudulent activities on the Ethereum network through a comprehensive performance comparison. The classifiers that showed the highest accuracy scores, which ranged from 0.9814 to 0.9862, were the Random Forest classifier, the visual gradient boosting machine, and the additive tree classifier. It is important to note that both Gradient Boosting Classifier and K Neighbors Classifier performed well, with accuracies above 0.96 and AUC scores above 0.99. However, some models, such as Naive Bayes, showed lower accuracy and AUC scores, suggesting that they have limitations in terms of accurately detecting fraudulent transactions. These results highlight the importance of choosing appropriate machine learning models for fraud detection tasks in general, with ensemble techniques such as Extra Trees and Random Forest showing great promise in this regard.
Anonymity is one of the characteristics that makes Bitcoin mainstream. However, various approaches have been proposed to deanonymize Bitcoin to reveal the identities of the people behind the addresses. In order to enhance anonymity, Bitcoin mixing services were developed to obscure links between Bitcoin addresses. CoinJoin transactions method is one of the most used mixing approaches. The CoinJoin technique is a concept where multiple users merge their transactions into one larger transaction [16]. In this article, we propose a new system of detecting CoinJoin transactions using machine learning. Firstly, we developed a new algorithm to extract connected transactions and trace them back to the Coinbase transaction. Afterwards, we conducted a rigorous analysis of the data and performed an ablation study to identify the most relevant features of our machine learning models. Then, we implemented and fine-tuned them using an automated tool called OPTUNA, after which we trained the models and evaluated their performances, including accuracy, precision, and F1 score.
This publication focuses on the use of the artificial intelligence for detecting anomalies, especially in the blockchain network. The research methodology includes the selection of anomalies to be detected and the processing of blockchain data. Various artificial intelligence methods were implemented for anomaly detection as part of the tests, and one new solution—a Fuzzy Neural Network—was presented. The findings indicate the possibility of detecting selected anomalies in the blockchain using artificial intelligence, which is of significant importance for the security of this technology. The conclusions present a discussion on limitations, future research prospects, and guidelines for future work.
Nurfajar Iskandar, Yusmanizar Yusmanizar, Andi Vita Sukmarini
The emergence of Non-Fungible Tokens (NFTs) technology has led to a significant transformation in the creative industry and media content realm, introducing fundamental new opportunities for the media sector as well as for the conservation and preservation of newspaper content. This research aims to analyze the impact of implementing Blockchain NFTs technology on the conservation and preservation of print newspaper content. This is motivated by the fact that many print media outlets have not yet adopted NFT technology, despite its potential to secure and provide economic value to both old and new print news content. The adoption of Blockchain NFTs technology is considered a forward-looking technology that offers excellent opportunities for the preservation of print newspaper content. This research uses a qualitative method to explore the impact of Blockchain NFTs technology on the conservation and preservation of print newspaper content. The research methods include literature review, in-depth interviews, and secondary data analysis. The findings indicate that implementing Blockchain NFTs technology can provide benefits such as better data security, transparency, and the potential for new economic value through the creation and trading of NFTs from historically or otherwise significant print newspaper content. Keywords: Blockchain, Conservation, NFTs, Newspapers, Preservation
Open access
Blockchain Technology Applications and Security
Advanced Steganography and Watermarking Techniques
Moiz Qureshi, Hasnain Iftikhar, Paulo Canas Rodrigues, Mohd Ziaur Rehman · 5 authors
Bitcoin (BTC-USD) is a virtual currency that has grown in popularity after its inception in 2008. BTC-USD is an internet communication network that makes using digital money, including digital payments, easy. It offers decentralized clearing of transactions and money supply. This study attempts to accurately anticipate the BTC-USD prices (Close) using data from September 2023 to September 2024, comprising 390 observations. Four machine learning models—Multi-layer Perceptron, Extreme Learning Machine, Neural Network AutoRegression, and Extreme-Gradient Boost—as well as four time series models—Auto-Regressive Integrated Moving Average, Auto-Regressive, Non-Parametric Auto-Regressive, and Simple Exponential Smoothing models—are used to achieve this end. Various hybrid models are then proposed utilizing these models, which are based on simple averaging of these models. The data-splitting technique, commonly used in comparative analysis, splits the data into training and testing data sets. Through comparison testing with training data sets consisting of 30%, 20%, and 10%, the present work demonstrated that the suggested hybrid model outperforms the individual approaches in terms of error metrics, such as the MAE, RMSE, MAPE, SMAPE, and direction accuracy, such as correlation and the MDA of BTC. Furthermore, the DM test is utilized in this study to measure the differences in model performance, and a graphical evaluation of the models is also provided. The practical implication of this study is that financial analysts have a tool (the proposed model) that can yield insightful information about potential investments.
Bitcoin, as one of the leading cryptocurrencies, has garnered significant attention due to its highly volatile market behavior. Accurate prediction of Bitcoin prices is crucial for investors, traders, and financial analysts who seek to navigate the uncertainties of this digital currency market. In recent years, machine learning algorithms have emerged as powerful tools for forecasting financial trends, with various models being tested for their ability to predict Bitcoin prices. Among these, the Novel Decision Tree Algorithm and K-Nearest Neighbor (K-NN) algorithm have been recognized for their potential in making accurate predictions. This study aims to improve the efficiency of Bitcoin market price prediction using the Novel Decision Tree Algorithm and to evaluate its performance in comparison with the K-Nearest Neighbor (K-NN) Algorithm. The analysis was conducted with a sample size of 20 for both groups, and a pretest power analysis was performed at an 80% power level. The software implementation of both algorithms resulted in a prediction precision of 87.80% for the Novel Decision Tree Algorithm and 86.91% for the K-NN Algorithm. To assess the statistical significance of the results, an independent sample t-test was conducted, revealing that the difference in accuracy between the two algorithms was statistically negligible, with a value of 0.745 ($p > 0.05$). Despite the small difference, the Novel Decision Tree Algorithm outperformed the K-NN Algorithm in terms of accuracy, demonstrating a higher precision in Bitcoin price prediction.
The proposed work builds upon the Random Forest machine learning algorithm to improve the process of digit forensic investigation in case of NFT. The following structure of this framework is aimed at identifying and disabling fraudulent or suspicious activities in NFT transactions by comparing different parameters like the Detection Time, False Positive Rate, the Total Transaction Volume Analyzed, the Anomalous Transaction Ratio, Clustering Accuracy, Data Utilization Efficiency, and Detection Sensitivity. Through using Random Forest, a solid ensemble learning technique that is well known for its on high accuracy as well as off overfitting tendency, it optimistically improves the identifying abilities of the framework in isolation of the false positives. The ability of the proposed system to deliver optimal results is further explained by line plots, area charts, histograms, and stem plots which all provide the variation of these metrics as the time proceeds. Not only does it enhance the effectiveness of detecting the fraudulent transactions, but it also enhances the application of data in the forensic analysis that creates a great advantage in the increasing realm of digital assets for investigators.
Non-fungible tokens (NFTs) are unique digital assets whose possession is defined over a blockchain. NFTs can represent multiple distinct objects such as art, images, videos, etc. There was a recent surge of interest in trading them which makes them another type of alternative investment. The inherent volatility of NFT prices, attributed to factors such as over-speculation, liquidity constraints, rarity, and market volatility, presents challenges for accurate price predictions. For such analysis and forecasting, machine learning methods offer a robust solution framework. Here, we focus on three related prediction problems over NFTs: Predicting NFTs sale price, inferring whether a given NFT will participate in a secondary sale, and predicting NFT's sale price change over time. We analyze and learn the visual characteristics of NFTs by deep pre-trained models and combine such visual knowledge with additional important non-visual attributes such as the sale history, seller's and buyer's centralities in the trading network, and collection's resale probability. We categorize input NFTs into six categories based on their characteristics. Across detailed experiments, we found visual attributes obtained from deep pre-trained models to increase the prediction performance in all cases, and EfficientNet seems to perform the best. In general, CNN and XGBoost consistently outperformed the rest of them across all categories. We also publish our novel NFT dataset with temporal price knowledge, which is the first dataset to have NFT prices over time rather than at a single time point. Our code and NFT datasets are publicly available at https://github.com/seferlab/deep_nft .
As a decentralized digital currency, the price of Bitcoin is affected by multiple factors and has complex and non-linear characteristics. Traditional time series forecasting methods such as ARIMA models have limitations in dealing with these characteristics. In order to overcome these problems, a prediction algorithm based on the ARIMA-LSTM combined model is proposed. This algorithm captures the linear trend of Bitcoin through ARIMA model, and then models the nonlinear features and time dependence through LSTM model to improve the accuracy of prediction. Experimental results show that compared with a single model, the ARIMA-LSTM combination model has better prediction performance when dealing with highly volatile assets such as Bitcoin, which provides a good foundation for digital currency risk management and risk management in the financial market. It provides new ideas for investment decisions.
Muhammad Hamdani, Silvia Ratna, Muhammad Muflih, Haldi Budiman · 6 authors
Bitcoin, the most widely used cryptocurrency, has garnered significant interest due to its volatile nature and the challenges associated with its price prediction. This paper presents a comparative study of various neural network algorithms for Bitcoin price prediction, utilizing daily trading data and multiple technical indicators. The models evaluated include Artificial Neural Networks (ANN), Recurrent Neural Networks (RNN), Convolutional Neural Networks (CNN), Backpropagation Neural Networks (BPNN), and Long Short-Term Memory (LSTM). A baseline comparison is conducted using Linear Regression (LR). Bayesian Optimization is employed to enhance the performance of these models by fine-tuning their hyperparameters. The study aims to determine the most effective model for accurate Bitcoin price prediction, which is crucial for both investors and market analysts. The results indicate that selective use of technical indicators and Bayesian Optimization significantly improves the MSE and RMSE scores of most models in this paper, compared to using only a base model without technical indicators.
Udayveer Singh Virk, Devansh Verma, Gagandeep Singh, Prof. Sheetal Laroiya Prof. Sheetal Laroiya
Abstract—This project aims to develop a web3 platform that stores user credentials on the blockchain, providing high levels of security and privacy. Using a range of tools and technologies, including Metamask, RemixIDE, Ganache, Node.js, Solidity for smart contracts, HTML, and CSS, the platform offers a user-friendly interface that enhances the user experience. Smart contracts are used to ensure that user credentials are only visible to the individual user, providing a high level of security and privacy. This platform has the ability to revolutionize how users interact with online services and manage their digital identities, reducing costs, increasing trust, and improving expandability. The implementation of this project has demonstrated the overall benefits of blockchain and smart contracts in virtual identity management, including increased security, improved privacy, and enhanced user experience. The platform has the potential for further development and expansion, including the integration of biometric authentication, artificial intelligence and machine learning algorithms, and the expansion to include a range of online services. Overall, this project has demonstrated the significant potential of blockchain technology and smart contracts in digital identity management and has the ability to shift the way users communicate with online services, offering a one-stop-shop for their online needs. Keywords—Block chain, metamask, ganache, remix ide, solidity
In recent years, there has been a growing interest in probabilistic forecasting methods that offer more comprehensive insights by considering prediction uncertainties rather than point estimates. This paper introduces a novel variational autoencoder learning framework for multivariate distributional forecasting. Our approach employs distributional learning to directly estimate the cumulative distribution function of future time series conditional distributions using the continuous ranked probability score. By incorporating a temporal structure within the latent space and utilizing versatile quantile models, such as the generalized lambda distribution, we enable distributional forecasting by generating synthetic time series data for future time points. To assess the effectiveness of our method, we conduct experiments using a multivariate dataset of real cryptocurrency prices, demonstrating its superiority in forecasting high-volatility scenarios.
The cryptocurrency is the encrypted, digital and peer-to-peer currency invented using blockchain technology in 2009. It is implemented as medium of exchange between computers of the network without interference from any centralised authority. The Bitcoin is most widely used and valuable cryptocurrency across the world. In India, also many people prefer the Bitcoin for their investment. People want to be more aware of the possibilities and opportunities that cryptocurrencies can present, to maintain the confidence and trust rate of utilising cryptocurrencies. The goal of this paper is to predict the future value of Bitcoin cryptocurrency in Indian Rupees (INR), with machine learning using Python. The dataset of approximately past 768 days from current date is trained to predict the INR value of Bitcoin for next 10 days.
This study explores the integration of blockchain technology in wearable health devices through the design and development of a Smart Fidget Toy. We aimed to investigate design challenges and opportunities of blockchain-based health devices, examine the impact of blockchain integration user experience, and assess its potential to improve data control and user trust. Using an iterative user-centered design approach, we developed a mid-fidelity prototype of a physical fidget device with a blockchain-based web application. Our key contributions include the design of a fidget toy using blockchain for secure health data management, an iterative development process balancing user needs with blockchain integration challenges, and insights into user perceptions of blockchain wearables for health. We conducted user studies, including a survey (n = 28), focus group (n = 6), interactive wireframe testing (n = 7), and prototype testing (n = 10). Our study revealed high user interest (70%) in blockchain-based data control and sharing features and improved perceived security of data (90% of users) with blockchain integration. However, we also identified challenges in user understanding of blockchain concepts, necessitating additional support. Our smart contract, deployed on the Polygon zkEVM testnet, efficiently manages data storage and retrieval while maintaining user privacy. This research advances the understanding of blockchain applications in health wearables, offering valuable insights for the future development of this field.