This paper aims to analyze cryptocurrency volatility by examining the effect of Gold, Dollar Index, and Composite Stock Price Index (IHSG) as independent variables and on Bitcoin and Ethereum as dependent variables. The cryptocurrency objects in this study are Bitcoin and Ethereum, which have the largest market capitalization. The data in this study used the period January 1, 2018, to December 31, 2021. This study used GARCH analysis. This study's results indicate that Bitcoin's volatility is influenced by the price of Bitcoin itself, gold, and the stock exchange index, and Ethereum and the stock exchange index influence Ethereum. This shows that the cryptocurrency market is inefficient as the prices are also affected by past prices.
Cryptocurrencies are digital currencies that operate on the blockchain, which is the technology that offers security and decentralization. The principal characteristic of cryptocurrencies is that they are not generally issued by a central authority. Many factors can influence the volatility of prices. This paper enables to drive insights into the behavior of markets through the application of sentiment analysis of Tweets, Google news and machine learning techniques for the challenging task of cryptocurrency price prediction. Most of the studies have focused exclusively on the sentiment analysis of tweets. In this work, we propose the use of common machine learning tools and available Google News data for predicting the price of crypto. We present the results of the Long Short-Term Memory (LSTM) model using Tweets and Google News data.
Harshith Singathala, Jyotsna Malla, J. Jayashree, J. Vijayashree
Bitcoin was introduced in 2009 and is the earliest cryp- tocurrency in the world. It has gained immense popularity and has attracted a huge consumer base owing to its ever-increasing market capitalization. This has led to many traders and investors being interested in knowing the future prices of these cryptocurrencies to gain profits. Researchers have contributed several works in the field of predicting the future cryptocurrency but with very low accuracy. The aim of this paper is to propose a bitcoin price prediction model which will help predict the future prices of bitcoin. Different deep-learning models are involved in the proposed prediction model namely Gated Recurrent Unit(GRU), Long Short-Term Memory(LSTM), Bidirectional GRU (BiGRU) and Bidirectional LSTM (BiLSTM). The performance analysis of the different models shows that BiGRU is able to predict the future bitcoin prices with the lowest Mean Absolute Error Percentage(MAPE) score of 3.41
The prediction of digital asset prices is a challenging task, as the value of digital assets is influenced by a multitude of factors, including market sentiment, technological advancements, and macroeconomic events. Despite these challenges, various approaches to digital asset price prediction have been proposed, including time-series analysis, machine learning (ML) algorithms, and Deep Learning (DL) algorithms. These algorithms involve using historical price data to make estimation about future price movements. It is important to note that digital asset price predictions are inherently uncertain and should be viewed as a guide rather than a definitive forecast. This proposed system can estimate the price for Non-Fungible Token(NFTs) collection as it can provide an accurate and reliable estimate of the value of these NFTs in the market. This information can help inform investment decisions, support market analysis, and improve the buying and selling experience for collections NFTs.
Cryptocurrency price prediction is most wanted by investors nowadays to get more money in cryptocurrency investment. All existing methods depicted in the survey for Cryptocurrencies price prediction are not suitable for real-time investment price prediction. To handle the above-mentioned issues, Recurrent Neural Network (RNN) with Long Short-Term Memory (LSTM) is anticipated for Cryptocurrency price prediction. The proposed method depends on machine learning technique, mostly in monetary fields for forecasting stock prices. Min-Max Scaler is used for pre-processing, changing the numeric values to the common scale in the dataset. LSTM is an Artificial Recurrent Neural Network (RNN) model employed in the deep learning field, and here it is used for cryptocurrency price prediction. Recurrent Neural Network (RNN) using LS TM can be accomplished in the proposed model, which proceeds with a set of working out sequences by using an optimization procedure like gradient descent with back transmission through time to calculate the gradients required through the progression of optimization in order to change each weight of the LSTM network to perform error calculation at the output layer of LSTM with respect to the corresponding weight. The proposed strategy involves the result from the model, which is considered as the another contribution for a similar model.
Due to the growing importance of the cryptocurrency market, as well as the diversity and expansion of online trading platforms, cryptocurrency technology has piqued the curiosity of a wide range of people, from market traders to researchers and analysts. Reliable price prediction is a necessity since investors face multiple challenges including market volatility, risk management, and market complexity. Therefore, numerous studies have been done using deep learning and machine learning algorithms to demonstrate their functionality and efficiency in this area. In this paper, we employed Bitcoin historical data to make predictions for the next day's closing price using a new hybrid 2D-CNNLSTM model with OPTUNA hyperparameter tuning. The dataset used to train the model was gathered using an automated web scraping technique. With the proposed model, the R2 error achieved 0.98166 and the MAPE was 0.034. Our proposed model is compared with three different models: CNN, LSTM, and GRU. The predicted results show that the proposed hybrid model is efficient for accurately predicting bitcoin prices and reliable for supporting investors to make their informed investment decisions. Additionally, the proposed model has outperformed other commonly used algorithms, namely CNN, LSTM, and GRU in terms of R2, and MAPE. This model is also capable of performing real-time forecasting.
Contemporarily, Bitcoin has enjoyed great popularity worldwide based on the development of the blockchain technology. Dozens of researches have been done on forecasting the price of bitcoin, however, the most accurate model remains inconclusive. This paper investigates the performances of Bitcoin price prediction based on ARIMA model and ordinary least square multifactorial linear model in terms of the dataset from May 2019--April 2022 in both short-term and long-term. According to the analysis, linear regression model outperforms ARIMA model in short term test which is significantly accurate. Nevertheless, in terms of long-term prediction, although the linear regression model still performs better than ARIMA model. None of them shows great accuracy on account of uncertain changes that some assumptions are no longer applicable. Therefore, these results shed light on guiding further exploration focusing on cryptocurrency pricing.
Ahmad Sani Bello, Jens Schneider, Roberto Di Pietro
Pump and Dump schemes represent a threat to any market. While this issue has long been regulated in mature markets, in unregulated markets, such as crypto exchanges, this plague is very present, and even exacerbated by the low capitalizaton of many cryptocurrencies that represent the perfect target for such a fraudulent scheme. In this paper, we detail a Low Latency Detection solution (LLD) based on deep learning to automatically detect pump and dump activities on centralized cryptocurrency exchanges. We train a LSTM-based auto-encoder on BTC valuations, which can reliably be considered a proxy for regular trading-due to their larger capitalization. We use this auto-encoder to predict valuations on alt coins and use thresholding on a Gaussian tail condition to trigger detection. We argue that low latency detection is paramount for the practicality of such approaches. Unlike previous methods, our solution (LLD) detects the majority of pumps in less than five minutes (2.2 minutes on average) when using OHLCV data at one-minute resolution. In addition, we use social media data only to generate ground truths during testing. We show that in many cases a significant amount of the trade volume could have been saved had LLD been used to trigger trade suspension mechanisms. The idiosyncratic approach of our scheme, its sound rationale and viability, combined with the quality of achieved results-tested over an extensive experimental campaign-and the insights discussed in the paper also pave the way for further research in the field.
Blockchain, the underlying technology of Bitcoin and several other cryptocurrencies, like Ethereum, produces a massive amount of open-access data that can be analyzed, providing important information about the network's activity and its respective token. The on-chain data have extensively been used as input to Machine Learning algorithms for predicting cryptocurrencies' future prices; however, there is a lack of study in predicting the future behaviour of on-chain data. This study aims to show how on-chain data can be used to detect cryptocurrency market regimes, like minimum and maximum, bear and bull market phases, and how forecasting these data can provide an optimal asset allocation for long-term investors.
Mr. R. Arunachalam, Myana Santhoshini, R. Tamil Prabha, R. Tamil Prabha
In this paper, we tried to estimate the Bitcoin price precisely taking into consideration various parameters that affect the Bitcoin value. In our work, we pointed to understand and identify daily changes in the Bitcoin market while obtaining insight into most appropriate features surrounding Bitcoin price. We will predict the daily price change with highest possible accuracy. The market capitalization of publicly traded cryptocurrencies is currently above $230 billion. Bitcoin, the most valuable cryptocurrency, serves primarily as a digital store of value, and its price predictability has been well-studied. For the first phase of our investigation, we aim to understand and identify daily trends in the Bitcoin market while gaining insight into optimal features surrounding Bitcoin price. Our data set consists of various features relating to the Bitcoin price and payment network over the course of five years, recorded daily. For the second phase of our investigation, using the available information, we will predict the sign of the daily price change with highest possible accuracy with deep learning algorithm such as long short term memory for greater accuracy. Compared with benchmark results for daily price prediction, we achieve a better performance, with the highest accuracies of the statistical methods and deep learning algorithms. Deep Learning models includes Long Short-Term Memory in RNN for Bitcoin price prediction are superior to statistical methods
Aims: This article investigates recent advancements in machine learning and blockchain technology for cryptocurrency price prediction. The study presents a ML system using various techniques applied to six different datasets. The findings highlight that simpler models can outperform complex ones in predicting cryptocurrency prices. Methods: The methods used in this study include applying diverse ML techniques such as LSTM, CNN, SVM, KNN, XGBoost, Astro ML, LASSO, RIDGE, linear regression, DT, and GP on six cryptocurrency datasets to predict prices. Results: The research evaluated various machine learning techniques for predicting cryptocurrency prices and reported the following RMSE values: Bitcoin prediction using Nadaraya-Watson kernel regression yielded an RMSE of 0.17, while Dogecoin prediction with linear regression resulted in an RMSE of 0.032. Ethereum price prediction using Gaussian regression achieved an RMSE of 0.02. For USD Coin, a combination of XGBoost, Gaussian regression, and Ridge techniques led to an RMSE of 0.014. Binance Coin price prediction using Gaussian regression had an RMSE of 0.032, and finally, Cardano Coin prediction employing LSTM reached an RMSE of 0.059. Conclusion: This study demonstrated the effectiveness of various machine learning techniques in predicting cryptocurrency prices. It revealed that simpler models can outperform complex ones in certain cases. The research contributes valuable insights to the field and can guide future work in cryptocurrency price prediction. The proposed model achieved promising results as evaluated by the RMSE metric.
Teknolojinin gelişmesiyle birlikte kripto para borsaları insanların daha fazla gelir elde etmek amacıyla kullandığı borsalardan biri olmuştur. Borsalarda alım-satım işlemleri yapılırken teknik ve temel analiz yöntemleri kullanılmaktadır. Teknik analiz, geçmiş verilerden yola çıkarak gelecekteki fiyat hareketlerini tahmin etme işlemidir. Teknik analiz yapılırken çok büyük verilerle karşılaşılınca verilerin analizi zorlaşmakta ve teknik analiz sonucu elde edilecek verilerin hatalı olma ihtimali artmaktadır. Bu durum sonucunda büyük verileri doğru analiz edemeyen yatırımcıların büyük zararlara uğrama ihtimali artmaktadır. Kripto para tahmini hem yatırımcılara doğru karar almak için hem de bilimsel alanda uygulamalara açık olduğu için değerlidir. Bu sebeple bu çalışmada, kripto para hareketliliği en yüksek olan kripto paralar arasından 3 adet kripto para seçilerek fiyat tahmini çalışması yapılmıştır. Seçilen kripto paralar; Bitcoin, Ethereum ve Cardano’dur. Verilerin büyük olması sebebiyle ve karar etkenlerinin analizi açısından Yapay Sinir Ağları ve Regresyon Analizi yöntemleri ile bu kripto paraların açılış, kapanış, gün içindeki en küçük ve en büyük değerleri kullanılarak bir sonraki günün kapanış değeri tahmin edilmiştir. Sonrasında tahmini değerlerle gerçek değerler arasında karşılaştırma yapılmıştır. Çalışma sonucunda Yapay Sinir Ağları ile yapılan tahmin çalışmasının Regresyon Analizi ile yapılan tahmin çalışmasından daha başarılı performans sergilediği gözlemlenmiştir.
The aim of this paper is to investigate the effect of a novel method called linear law-based feature space transformation (LLT) on the accuracy of intraday price movement prediction of cryptocurrencies. To do this, the 1-minute interval price data of Bitcoin, Ethereum, Binance Coin, and Ripple between 1 January 2019 and 22 October 2022 were collected from the Binance cryptocurrency exchange. Then, 14-hour nonoverlapping time windows were applied to sample the price data. The classification was based on the first 12 hours, and the two classes were determined based on whether the closing price rose or fell after the next 2 hours. These price data were first transformed with the LLT, then they were classified by traditional machine learning algorithms with 10-fold cross-validation. Based on the results, LLT greatly increased the accuracy for all cryptocurrencies, which emphasizes the potential of the LLT algorithm in predicting price movements.
The growing potential and high volatility of the cryptocurrency market attract a lot of interest from both businesses and investors. Even though the prices fluctuate, predicting with time serious models such as ARMA and ARIMA would still provide a useful reference for analyzing the market. Recent studies on machine learning methods including RNNs have made new progress in forecasting digital currencies. This study focuses on one of the traditional models ARMA to predict the time serious dataset from 2021-2022 of cryptocurrencies including Bitcoin, Ethereum and Ripple. To be specific, AIC and ADF tests are used to choose the optimal model and suitable dataset. According to the analysis, the ARMA model would be affected by the volatility of Bitcoin. However, the predictions are not precise enough but still a valuable reference for certain businesses and individual investors. More state-of-art machine learning models can be utilized in future study to enhance the performance. Overall, these results shed light on guiding further exploration of crypto currency price prediction.
Harendra Kumar Narang, Vishal K. Shrirame, Bhupesh Kurrey
Predicting or forecasting crypto currency prices is now one of the most difficult tasks in crypto market trading due to its qualities and dynamic nature. The purpose of the present work is to analyse the exchange and blockchain data and develop a prediction model using machine learning. Ethereum (ETH) is one of the crypto currencies, and data has been taken from the price time series from January 1, 2017 to December 31, 2021, on a daily basis. The algorithm for gathering data has been trained and tested using a machine-learning algorithm. The adequacy of the developed machine learning models was validated using MAPE, RSME, MAE, and R2 scores. The developed model can predict future results with an accuracy of up to 85% for 7 days. Based on the findings, it is suggested that blockchain historical data and exchange data can be utilised as input characteristics in the development of a machine learning model to forecast Ethereum's future price.
Yapılan bu çalışmanın amacı, 1.1.2016-4.12.2022 dönemini kapsayan günlük veriler yardımıyla Bitcoin ile alakalı çıkan haberler ile hem Bitcoin fiyatı hem de getirisi arasındaki ilişkiyi zamanla değişen nedensellik analizi kapsamında incelemektir. Söz konusu ilişkinin varlığı, Hacker ve Hatemi-J (2006)’nin Boostrapt Temelli Toda-Yamamoto Nedensellik Testi ve zamanla değişen nedensellik analizi kullanılarak araştırılmıştır. Elde edilen nedensellik testi bulguları, Bitcoin ile ilgili çıkan haberler ile Bitcoin fiyatı arasında karşılıklı bir nedensellik ilişkisi olduğu yönündedir. Diğer taraftan, Bitcoin getirisi ile Bitcoin ile ilgili çıkan haberler arasındaki nedensellik bulguları incelendiğinde, Bitcoin ile alakalı çıkan haberlerden Bitcoin getirisine doğru nedensellik ilişkisinin söz konusu olmadığı, buna karşın Bitcoin getirilerinden Bitcoin ile alakalı çıkan haberlere doğru bir nedensellik olduğu söylenebilir. Ayrıca, söz konusu nedensellik ilişkilerinin zamanla nasıl bir seyir izlediğine bakıldığında özellikle Bitcoin fiyatlarının arttığı dönemlerde Bitcoin ile ilgili haber sayılarının arttığı görülmüştür. Bu çerçevede hem Bitcoin hem de altcoin piyasasına yatırım yapacak bireylerin, Bitcoin ve altcoin ile alakalı çıkmış olan haberleri dikkate alarak işlem yapmaları yatırımın sağlıklı olması adına önem teşkil etmektedir.
Vasileios Kochliaridis, Eleftherios Kouloumpris, Ioannis Vlahavas
Abstract Cryptocurrency markets experienced a significant increase in the popularity, which motivated many financial traders to seek high profits in cryptocurrency trading. The predominant tool that traders use to identify profitable opportunities is technical analysis. Some investors and researchers also combined technical analysis with machine learning, in order to forecast upcoming trends in the market. However, even with the use of these methods, developing successful trading strategies is still regarded as an extremely challenging task. Recently, deep reinforcement learning (DRL) algorithms demonstrated satisfying performance in solving complicated problems, including the formulation of profitable trading strategies. While some DRL techniques have been successful in increasing profit and loss (PNL) measures, these techniques are not much risk-aware and present difficulty in maximizing PNL and lowering trading risks simultaneously. This research proposes the combination of DRL approaches with rule-based safety mechanisms to both maximize PNL returns and minimize trading risk. First, a DRL agent is trained to maximize PNL returns, using a novel reward function. Then, during the exploitation phase, a rule-based mechanism is deployed to prevent uncertain actions from being executed. Finally, another novel safety mechanism is proposed, which considers the actions of a more conservatively trained agent, in order to identify high-risk trading periods and avoid trading. Our experiments on 5 popular cryptocurrencies show that the integration of these three methods achieves very promising results.
Apr 19, 2023·2023 International Conference on Recent Advances in Electrical, Electronics, Ubiquitous Communication, and Computational Intelligence (RAEEUCCI)
Bitcoin (BTC) is a cryptocurrency meaning that it is a virtual asset that works on encryption systems to control production of units and verify the funds transfer. Bitcoin's operation is independent of central bank and can be used as a decentralized medium of exchange. Being an emerging domain, the blockchain systems on which these cryptocurrencies are based, are a great source of investment among enthusiasts. However, there is high volatility in the price of Bitcoin and thus it paves the way for its prediction so as to get a clear insight on its trend. Forecasting Bitcoin prices can provide valuable insights for investment portfolio management, risk assessment, and the identification of profitable trading or arbitrage opportunities. Furthermore, Bitcoin price predictions may assist firms that accept Bitcoin payments in enhancing their financial management practices by improving their revenue and cash flow forecasting. Additionally, governmental entities and regulatory bodies could leverage Bitcoin price forecasting as a tool for monitoring and regulating the cryptocurrency industry. This paper explores the effectiveness of ML models in predicting Bitcoin price by analyzing a diverse set of historical data. We evaluate several ML algorithms, and compare their performance in terms of accuracy to find out best algorithms for short term and long-term Bitcoin price prediction.
Nurazlina Abdul Rashid, Mohd Tahir Ismail, Noor Wahida Md Junus
Predicting cryptocurrency prices are difficult due to dynamic data. At the same time, the hidden market behavior of trend and seasonal components in the history data is also critical as it provides an idea of what the price pattern will be in the future. Hence, this research proposes to identify and model the hidden pattern behavior in terms of component time series instead of removing it via the linear structural time series (STS) model approach. This study focuses on the top five cryptocurrencies relying on the highest market capitalization. From the results obtained, the top five cryptocurrencies have a different trend model, either deterministic or stochastic, which relies on the behavior of data. The five cryptocurrencies also show the crypto winter event, where the trend is downward after six months every year. The linear STS is the best model for predicting three cryptocurrencies’ prices for nonstationary and volatility data behavior. It can also handle the hidden component behavior and is easy to interpret. Since the linear STS model can indirectly retain the information of data, it will assist investors and traders in accurately predicting cryptocurrency prices.
Recently, due to the ease of buying and selling cryptocurrencies and the continuous influence of social media, people have invested in the cryptocurrency market to obtain passive income. However, the volatility of the cryptocurrency market has caused many investors to lose their money. Although most people are aware of the high risks of cryptocurrencies along with the high rate of return, investing in cryptocurrencies has always been a topic of continuous discussion among researchers and investors. With the development of artificial intelligence (AI) and machine learning, machine learning has been applied to financial investment, and the research effect is remarkable recently. Thus, we propose a new self-adaptive trading system based on box theory and the K-means clustering algorithm. In the box theory, good buying or selling points occur when the oscillation box is broken and falls upward or below to enter the next box. This system predicted the upper and lower boundaries of the Oscillation Box through the K-means clustering algorithm and the sliding window method. Because of the sliding window method, prediction becomes more flexible and can be used in the market with the obtained upper and lower boundaries in a trading system. We also evaluated various market conditions (bull market, bear market, and fluctuant market) to construct the best K-means trading algorithm. After using Ethereum for backtesting, in the 4-month of July to November 2022), the transaction showed a 75 % winning rate, the final Return on Investment (ROI) of 33%, and a market gain of around 6%. This trading model is equipped with the ability of self-adjustment so that investors do not need to put effort on the market while maintaining a stable and considerable return on investment.
As the price of virtual currency fluctuates greatly, precise prediction and appropriate trading strategies can bring investors best returns. This paper predicted the price of Ethereum and Bitcoin in the light of autoregressive integrated moving average model (ARIMA) and get a R2 of 0.995 and 0.993 respectively, which indicates the model can yield reasonable predictions. Then their investment ratios are set to 0.88 and 1.12 respectively by analytic hierarchy process (AHP). Particle swarm optimization (PSO) is used to solve the daily revenue function formed by the predicted price and the current price. Finally, the paper compared the returns yielded by the PSO trading strategy optimized by AHP and the strategy without optimization. It can be concluded that the AHP has a possibility of 64.66 per cent to yield more returns when used.