Summary This study explores various machine learning and deep learning applications on financial data modelling, analysis and prediction processes. The main focus is to test the prediction accuracy of cryptocurrency hourly returns and to explore, analyse and showcase the various interpretability features of the ML models. The study considers the six most dominant cryptocurrencies in the market: Bitcoin, Ethereum, Binance Coin, Cardano, Ripple and Litecoin. The experimental settings explore the formation of the corresponding datasets from technical, fundamental and statistical analysis. The paper compares various existing and enhanced algorithms and explains their results, features and limitations. The algorithms include decision trees, random forests and ensemble methods, SVM, neural networks, single and multiple features N‐BEATS, ARIMA and Google AutoML. From experimental results, we see that predicting cryptocurrency returns is possible. However, prediction algorithms may not generalise for different assets and markets over long periods. There is no clear winner that satisfies all requirements, and the main choice of algorithm will be tied to the user needs and provided resources.
People are starting to see the cryptocurrency market as a viable source of income and investment, similar to the stock market, as the concept of cryptocurrencies continues to gain popularity. Predicting Bitcoin returns is related to financial machine learning, which uses time series to forecast price variance. This study starts with the daily close price of Bitcoin for its initial dataset. The price is transformed into percentages and binary classes, which categorize into “Up” and “Down”, after which a time series is applied to produce two datasets: a categorical dataset for classification and a numerical dataset for regression. For classification that represents a Binary classification in asset-price forecasting, k-fold cross-validation is applied to ensure that the best classifiers are selected for testing and analysis. Most of the regression analysis was based on visualization, which displayed the predicted prices by each regressor in front of the original values and helped analyze the models’ results more accurately. The outcomes of this study were achieved by anticipating bitcoin returns using classification and regression machine learning models, despite the approaches’ low accuracy and significant precision rate to the “Up” class. At this stage, with a significant limitation regarding the dataset and a lack of other indicators, a model capable of predicting future variations is considered a beneficial addition for many trading tools or even for crypto market analysts.
Saachin Bhatt, Mustansar Ali Ghazanfar, Mohammad Hossein Amirhosseini
The purpose of this research is to investigate the impact of social media sentiments on predicting the Bitcoin price using machine learning models, with a focus on integrating onchain data and employing a Multi Modal Fusion Model. For conducting the experiments, the crypto market data, on-chain data, and corresponding social media data (Twitter) has been collected from 2014 to 2022 containing over 2000 samples. We trained various models over historical data including K-Nearest Neighbors, Logistic Regression, Gaussian Naive Bayes, Support Vector Machine, Extreme Gradient Boosting and a Multi Modal Fusion. Next, we added Twitter sentiment data to the models, using the Twitter-roBERTa and VADAR models to analyse the sentiments expressed in social media about Bitcoin. We then compared the performance of these models with and without the Twitter sentiment data and found that the inclusion of sentiment feature resulted in consistently better performance, with TwitterRoBERTa-based sentiment giving an average F1 scores of 0.79. The best performing model was an optimised Multi Modal Fusion classifier using Twitter-RoBERTa based sentiment, producing an F1 score of 0.85. This study represents a significant contribution to the field of financial forecasting by demonstrating the potential of social media sentiment analysis, onchain data integration, and the application of a Multi Modal Fusion model to improve the accuracy and robustness of machine learning models for predicting market trends, providing a valuable tool for investors, brokers, and traders seeking to make informed decisions
Bitcoin is a kind of Cryptocurrency and now is one of type of investment on the stock market.Stock markets are influenced by many risks of factor.And bitcoin is one kind of cryptocurrency that keep rising in recent few years, and sometimes sudden fall without knowing influence behind it on the stock market.Because it's fluctuations, there's a need and automation tool to predict bitcoin on the stock market.This research study learns how to create model prediction bitcoin stock market prediction using LSTM, LSTM (Long Short Term Memory) is another type of module provided for RNN later developed and popularized by many researchers, like RNN, the LSTM also consists of modules with recurrent consistency.The contribution of this study is providing a new forecasting framework for bitcoin price prediction can overcome and improve the problem of input variables selection in LSTM without strict assumptions of data assumption.The results revealed its possible applicability in various cryptocurrencies prediction, industry instances such as medical data or financial timeseries data.The Method that we apply on this research, also technique and tools to predict Bitcoin on stock market yahoo finance can predict the result above $ 12600 USD for next days after prediction, in the last section we make conclusions and discuss future works.The proposed methodology is then applied to train a simple Long Short Term Memory (LSTM) model to predict the bitcoin price for the upcoming 5 days.When the LSTM model is trained with a suitable data chunk, thus identified, sustainable results are found for the prediction.In the end of this paper, the work culminates with future improvements.
This research paper presents a stacked ensemble model for next day Bitcoin price prediction, incorporating diverse look-back windows and evaluating the performance of various models within the ensemble framework using metrics like Root Mean Squared Error (RMSE) and Mean Absolute Error (MAE). The base layer, layer-0, comprises LSTM and GRU models with different look-back windows. The layer-1 models, including CNN, SVR, Linear Regression, Random Forest Regressor, LSTM, and KNN, are tested individually in conjunction with the base layer models. Extensive experiments demonstrate the effectiveness of the stacked ensemble approach, improving prediction accuracy. The comparative analysis provides insights into the strengths and weaknesses of each model, aiding in the identification of optimized combinations for Bitcoin price prediction. This research contributes to the field by showcasing the value of diverse look-back windows and evaluating models in a stacked ensemble framework, enhancing the accuracy of Bitcoin price forecasting.
Rasoul Amirzadeh, Dhananjay Thiruvady, Asef Nazari, Mong Shan Ee
Abstract Cryptocurrencies have gained widespread attention, particularly in finance and investment sectors. Despite their growing popularity, cryptocurrencies can be a high-risk investment due to their price volatility. The inherent volatility in cryptocurrency prices, coupled with the effects of external global economic factors, makes predicting their price movements challenging. To address this challenge, we propose a dynamic Bayesian network (DBN)-based approach to uncover potential causal relationships among various features including social media data, traditional financial market factors, and technical indicators. This study focuses on six major cryptocurrencies, including Bitcoin, Binance Coin, Ethereum, Litecoin, Ripple, and Tether. The proposed model’s performance is compared to five baseline models of auto-regressive integrated moving average, support vector regression, long short-term memory, random forests, support vector machines, and a large language model. Results demonstrate that while DBN performance varies across cryptocurrencies, with some cryptocurrencies exhibiting higher predictive accuracy than others, the DBN significantly outperforms the baseline models.
Parth Daxesh Modi, Kamyar Arshi, Pertami J. Kunz, Abdelhak M. Zoubir
Bitcoin as a cryptocurrency has been one of the most important digital coins and the first decentralized digital currency. Deep neural networks, on the other hand, has shown promising results recently; however, we require huge amount of high-quality data to leverage their power. There are some techniques such as augmentation that can help us with increasing the dataset size, but we cannot exploit them on historical bitcoin data. As a result, we propose a shallow Bidirectional-LSTM (Bi-LSTM) model, fed with feature engineered data using our proposed method to forecast bitcoin closing prices in a daily time frame. We compare the performance with that of other forecasting methods, and show that with the help of the proposed feature engineering method, a shallow deep neural network outperforms other popular price forecasting models.
Farman Ullah Khan, Faridoon Khan, Parvez Ahmed Shaikh
Abstract The study aims at forecasting the return volatility of the cryptocurrencies using several machine learning algorithms, like neural network autoregressive (NNETAR), cubic smoothing spline (CSS), and group method of data handling neural network (GMDH-NN) algorithm. The data used in this study is spanning from April 14, 2017, to October 30, 2020, covering 1296 observations. We predict the volatility of four cryptocurrencies, namely Bitcoin, Ethereum, XRP, and Tether, and compare their predictive power in terms of forecasting accuracy. The predictive capabilities of CSS, NNETAR, and GMDH-NN are compared and evaluated by mean absolute error (MAE) and root-mean-square error (RMSE). Regarding the return volatility of Bitcoin and XRP markets, the forecasted results remarkably suggest that in contrast to rival approaches, the CSS can be an effective model to boost the predicting accuracy in the sense that it has the lowest forecast errors. Considering the Ethereum markets’ volatility, the MAE and RMSE associated with NNETAR are smaller than the MAE and RMSE of CSS and GMDH-NN algorithm, which ensures the effectiveness of NNETAR as compared to competing approaches. Similarly, in case of Tether markets’ volatility, the corresponding MAE and RMSE reveal that the GMDH-NN algorithm is an efficient technique to enhance the forecasting performance. We notice that no single tool performed uniformly for all cryptocurrency markets. The policymakers can adopt the model for forecasting cryptocurrency volatility accordingly.
Kripto para piyasası ulaştığı işlem hacmiyle geleneksel para piyasasına rakip duruma gelmiştir. Kripto para piyasasında coinlere alternatif olarak altcoinler piyasaya sunulmuştur. Kripto para piyasasına binlerce coin ve altcoin sunulmasına karşın bitcoinin büyüklüğüne ulaşamamışlardır. Kripto piyasası tezgahüstü bir piyasadır. Bu piyasanın volatilitesi ve riski oldukça yüksektir. Bu piyasanın yüksek getiri imkanı vermesi nedeniyle yatırımcıların ilgi odağı olmaktadır. Çalışmanın amacı kripto para birimlerinin fiyat hareketliliği temel alınarak, bu kripto paralar arasındaki eş-bütünleşme ve nedensellik ilişkileri incelenmektedir. Çalışma kapsamındaki kripto paralar Johansen Eş-bütünleşme Analizi ve Granger Nedensellik Testi kullanılarak incelenmiştir. Johansen eş-bütünleşme test sonucunda iz istatistiği ve max öz değer istatistikleri %5 anlamlılık düzeyindeki kritik değerden yüksek olduğu, H0 hipotezinin reddedildiği ve kripto para serileri arasında eş-bütünleşme ilişkisinin bulunduğunu ortaya koymuştur. Granger Nedensellik Test sonuçları, ADA, BNB, DOGE ve ETH’nin BTC’nin ‘nedeni’ ve BTC’nin ADA, BNB, DOGE ve ETH’nin ‘nedeni’ olduğu ve aralarında çift taraflı bir ilişkisinin bulunduğu belirlenmiştir. ETH ve SOL’un BTC’nin ‘nedeni’ olduğu ve aralarında tek taraflı bir ilişkisinin olduğu görülmüştür. Anahtar Kelimeler: Cryptocurrency, Johansen Cointegration Analysis, Granger Causality Test
Over the past decade, Bitcoin’s unprecedented performance has underscored its po-sition as the premier asset class. Starting from an insignificant value and reaching an astounding high of around 65,000 U.S dollars in 2021 – all without a central con-trolling authority – Bitcoin’s trajectory is undoubtedly a historical feat. Its intangible nature, initially a subject of skepticism, has turned into an attractive quality, leading many investors to allocate a significant portion of their portfolios to Bitcoin. The traditional banking and investment sectors have also turned their attention to Bitcoin’s exponential growth. Concurrently, research on macro-economic variables and investor sentiment explaining Bitcoin’s price fluctuations has seen considerable development. However, there is a notable absence of studies leveraging On-Chain Data, information derived from transaction data in Bitcoin’s blockchain network. This paper fills this gap by using LSTM (Long Short-Term Memory), a technique widely utilized for time-series data prediction, in conjunction with On-Chain Data, to predict Bitcoin prices.
Abstract Due to the highly volatile tendency of Bitcoin, there is a necessity for a better price prediction model. Only a few researchers have focused on the feasibility to apply various modelling approaches. These approaches may prone to have low convergence issues in outcomes and acquire high computation time. Hence a model is put forward based on machine learning techniques using regression algorithm and Particle Swarm Optimization with XGBoost algorithm, for more precise prediction outcomes of three cryptocurrencies; Bitcoin, Dogecoin, and Ethereum. The approach uses time series that consists of daily price information of cryptocurrencies. In this paper, the XGBoost algorithm is incorporated with an enhanced PSO method to tune the optimal hyper-parameters to yield out better prediction output rate. The comparative assessment delineated that the proposed method shows less root mean squared error, mean absolute error and mean squared error values. In this aspect, the proposed model stands predominant in showing high efficiency of prediction rate.
Abstract This study aims to evaluate forecasting properties of classic methodologies (ARCH and GARCH models) in comparison with deep learning methodologies (MLP, RNN, and LSTM architectures) for predicting Bitcoin's volatility. As a new asset class with unique characteristics, Bitcoin's high volatility and structural breaks make forecasting challenging. Based on 2753 observations from 08-09-2014 to 01-05-2022, this study focuses on Bitcoin logarithmic returns. Results show that deep learning methodologies have advantages in terms of forecast quality, although significant computational costs are required. Although both MLP and RNN models produce smoother forecasts with less fluctuation, they fail to capture large spikes. The LSTM architecture, on the other hand, reacts strongly to such movements and tries to adjust its forecast accordingly. To compare forecasting accuracy at different horizons MAPE, MAE metrics are used. Diebold–Mariano tests were conducted to compare the forecast, confirming the superiority of deep learning methodologies. Overall, this study suggests that deep learning methodologies could provide a promising tool for forecasting Bitcoin returns (and therefore volatility), especially for short-term horizons.
The long short-term memory (LSTM) network and a cutting-edge method that combines wavelet decomposition and LSTM (W-LSTM) were applied to deep learning in this study's analysis of Bitcoin's price and movement. To be specific, it predicted next day’s both price and price movement (trend) with historical data. The input of the model is close price itself, basic trading information, and technical indicators calculated solely on basic trading information. Large number of numerical experiments come to the same conclusion that: for price prediction, only close price as input obtains the best performance for regression, and minor improvement achieved after 1-order wavelet decomposition; for price movement, no improvement after changing the number of input features or with the model W-LSTM has been spotted for the same network structure and hyper-parameters, and enlarging time step and batch size will improve accuracy and Matthews correlation coefficient despite of number of input and model used in this paper.
K. Dhivya, B Akoramurthy, B Surendiran, T. Sivakumar
Different sectors are being revolutionized by distributed ledger technology.According to the 2022 market valuation, Hyperledger is now the second-largestblockchain platform for smart contracts. The creation of numerous apps maybe sped up and simplified with smart contracts, but there are certain drawbacks as well. For instance, vulnerability contracts are created intentionallyto weaken candor, smart contracts are employed to conduct fraudulent activities, and there are many redundant contracts that squander the efficiency ofthe system for no real reason. To solve these problems, we provide in thisresearch Service Level Agreement(SLA) for Hyperledger smart contracts. Wecreated Hyperledger smart contracts and focused on how smart contracts andconsumers used data. By manually analyzing the transactions, we were ableto extract four behavioral characteristics that may be used to differentiatebetween various contract types. Then, a smart contract is built using theseto include 14 fundamental functionalities. We provide a data splitting algorithm for splitting the gathered smart contracts in order to create the experimental dataset. Then, we train and test our dataset using an LSTM network.The comprehensive experimental findings demonstrate that our method can discriminate between various contract types and may be used to identify maliciouscontracts and detect anomalies with acceptable precision, recall, and F1-score.
With the rapid development of data science, quantitative trading models have become prevalent in financial markets. We calculate a series of indices based on the price data of gold and bitcoin from 2016 to 2021. On the basis of ARIMA model in time series algorithm, we build a prediction model that forecasts that very day's gold and bitcoin price relying solely on the past stream of daily prices to date. After completing the construction of the prediction model, we establish the quantitative trading model. We use AHP method to get buying scores of gold and bitcoin, which are the criteria for buying and selling. We then draw up some numbers and compare them with buying scores to decide whether to buy or sell and the number of shares bought and sold each day. After this, we use dynamic programming to find the theoretical maximum profit. Comparing this with the result of our quantitative trading model, we conclude that our model has significant superiority. Generally, the trading model established in this paper has good sensitivity to adapt to market changes and has strong risk resistance.
This paper presents an advanced econometric model specifically designed to analyze the intricate relationship between blockchain technology and various economic variables. The model serves as a robust framework for comprehending the impact of blockchain on investment patterns, adoption rates, and market trends. By quantifying these relationships, the model enables predictions regarding future trends in the blockchain industry and facilitates the identification of factors influencing growth or hindering adoption. With its wide-ranging applicability, the model offers profound insights for policymakers, investors, entrepreneurs, and researchers, shedding light on the economic implications of this rapidly evolving technology.The findings of this study reveal a multitude of significant insights regarding the economic implications of blockchain technology. The econometric model demonstrates a strong positive relationship between blockchain investment and adoption rates, indicating that increased investment leads to higher adoption levels. Moreover, the model identifies specific market trends and factors that influence the growth and adoption of blockchain technology. By highlighting these factors, stakeholders can make informed decisions and strategize accordingly.The econometric model forblockchain technology offers numerous applications and implications for various stakeholders. Policymakers can leverage the model's insights to develop regulatory frameworks that foster blockchain innovation while mitigating risks. Investors can utilize the model to make data-driven investment decisions and identify lucrative opportunities within the blockchain industry. Entrepreneurs can gain valuable insights into the factors driving adoption and tailor their business strategies accordingly. Additionally, researchers can expand their understanding of the relationship between technology and economic variables, contributing to the development of new theories and frameworks.
This study extends the examination of the Efficient-Market Hypothesis in Bitcoin market during a five year fluctuation period, from September 1 2017 to September 1 2022, by analyzing 28,739,514 qualified tweets containing the targeted topic "Bitcoin". Unlike previous studies, we extracted fundamental keywords as an informative proxy for carrying out the study of the EMH in the Bitcoin market rather than focusing on sentiment analysis, information volume, or price data. We tested market efficiency in hourly, 4-hourly, and daily time periods to understand the speed and accuracy of market reactions towards the information within different thresholds. A sequence of machine learning methods and textual analyses were used, including measurements of distances of semantic vector spaces of information, keywords extraction and encoding model, and Light Gradient Boosting Machine (LGBM) classifiers. Our results suggest that 78.06% (83.08%), 84.63% (87.77%), and 94.03% (94.60%) of hourly, 4-hourly, and daily bullish (bearish) market movements can be attributed to public information within organic tweets.
Amogh Shukla, Tapan Kumar Das, Sanjiban Sekhar Roy
TRON is a decentralized digital platform that provides a reliable way to transact in cryptocurrencies within a decentralized ecosystem. Thanks to its success, TRON’s native token, TRX, has been widely adopted by a large audience. To facilitate easy management of digital assets with TRON Wallet, users can securely store and manage their digital assets with ease. Our goal is first to develop a methodology to predict the future price using regression and then move on to build an effective classifier to predict whether a profit or loss is made the next day and then make a prediction of the transaction success rate. Our framework is capable of predicting whether there will be a profit in the future based on price prediction and forecasting results using regressors such as XGBoost, LightGBM, and CatBoost with R2 values of 0.9820, 0.9825 and 0.9858, respectively. In this work, an ensemble-based stacking classifier with the Whale optimization approach has been proposed which achieves the highest accuracy of 89.05 percent to predict if there will be a profit or loss the next day and an accuracy of 98.88 percent of TRX transaction success rate prediction which is higher than accuracies obtained by standard machine learning models. An effective framework will be useful for better decision-making and management of risks in a cryptocurrency.
Price feeds of securities is a critical component for many financial services, allowing for collateral liquidation, margin trading, derivative pricing and more. With the advent of blockchain technology, value in reporting accurate prices without a third party has become apparent. There have been many attempts at trying to calculate prices without a third party, in which each of these attempts have resulted in being exploited by an exploiter artificially inflating the price. The industry has then shifted to a more centralized design, fetching price data from multiple centralized sources and then applying statistical methods to reach a consensus price. Even though this strategy is secure compared to reading from a single source, enough number of sources need to report to be able to apply statistical methods. As more sources participate in reporting the price, the feed gets more secure with the slowest feed becoming the bottleneck for query response time, introducing a tradeoff between security and speed. This paper provides the design and implementation details of a novel method to algorithmically compute security prices in a way that artificially inflating targeted pools has no effect on the reported price of the queried asset. We hypothesize that the proposed algorithm can report accurate prices given a set of possibly dishonest sources.
The increasing popularity of cryptocurrencies as a means of financial inclusion for investment and trade has become a major concern for individuals seeking to benefit from the cryptocurrency market. This study aims to provide insights for cryptocurrency investors, financial sector professionals, and academics by utilizing machine learning techniques such as ARIMA and LSTM to compare the accuracy of modeling performance on datasets predicting the prices of five cryptocurrencies, namely Bitcoin, Ethereum, Binance Coin, Tether, and Cardano. Data was obtained by downloading from the Yahoo Finance website using Jupyter notebook. The LSTM method outperformed the ARIMA method, achieving a lower MAPE value of less than 10 percent and effectively capturing price movements, providing valuable information for decision-making.
The concept of digital cash has the potential to completely change how people think about money. Digital currency has emerged as a possible alternative for exchanging currency and traditional payment systems, in addition to a popular investment option due to its potential for high returns. One of the three main varieties of digital currency is cryptocurrency that is secured by blockchain technology. Bitcoin, Ethereum, and many other cryptocurrencies exist in crypto markets. Investing in cryptocurrencies still carries risks and uncertainties due to the price volatility. It is thus important to approach such investments with caution and thoroughly research the market and its risks before making investment decisions. This paper presents an application of AI technology for learning the price movement of Ethereum (ETH) which is second only to Bitcoin in market capitalization. Based on the Technical factor, the XGBoost model is constructed for classification of return on Ethereum close price. The technical indicators such as moving averages and relative strength index, together with the Bitcoin price trend are chosen to determine influence on Ethereum price further used for computing the short-term return separate into 3 classes: downtrend, sideway, and uptrend. The model performance is measured by multiclass ROC-AUC, achieving the micro-average ROC-AUC of 0.66 saying the model is reasonably good at predicting the overall trend of ETH price.
In this paper we predict Bitcoin movements by utilizing a machine-learning framework. We compile a dataset of 24 potential explanatory variables that are often employed in the finance literature. Using daily data from 2nd of December 2014 to July 8th 2019, we build forecasting models that utilize past Bitcoin values, other cryptocurrencies, exchange rates and other macroeconomic variables. Our empirical results suggest that the traditional logistic regression model outperforms the linear support vector machine and the random forest algorithm, reaching an accuracy of 66%. Moreover, based on the results, we provide evidence that points to the rejection of weak form efficiency in the Bitcoin market.