Bitcoin, with its ever-growing popularity, has demonstrated extreme price volatility since its origin. This volatility, together with its decentralised nature, make Bitcoin highly subjective to speculative trading as compared to more traditional assets. In this paper, we propose a multimodal model for predicting extreme price fluctuations. This model takes as input a variety of correlated assets, technical indicators, as well as Twitter content. In an in-depth study, we explore whether social media discussions from the general public on Bitcoin have predictive power for extreme price movements. A dataset of 5,000 tweets per day containing the keyword `Bitcoin' was collected from 2015 to 2021. This dataset, called PreBit, is made available online. In our hybrid model, we use sentence-level FinBERT embeddings, pretrained on financial lexicons, so as to capture the full contents of the tweets and feed it to the model in an understandable way. By combining these embeddings with a Convolutional Neural Network, we built a predictive model for significant market movements. The final multimodal ensemble model includes this NLP model together with a model based on candlestick data, technical indicators and correlated asset prices. In an ablation study, we explore the contribution of the individual modalities. Finally, we propose and backtest a trading strategy based on the predictions of our models with varying prediction threshold and show that it can used to build a profitable trading strategy with a reduced risk over a `hold' or moving average strategy.
The fame of cryptocurrencies soars in 2017 because of a few consecutive months of the exponential development of their market capitalization. Even though machine learning has been fruitful in anticipating stock market costs through a large group of various time series models, its application in foreseeing cryptocurrency costs has been very prohibitive. The reason behind this is clear as the costs of cryptocurrencies rely upon a ton of factors like technological progress, internal competition, pressure on the markets to deliver, economic problems, security issues, political factors and so on Their high volatility prompts the incredible capability of high benefit if savvy designing systems are taken. Sadly, because of their absence of lists, cryptocurrencies are somewhat capricious contrasted with traditional financial predictions like stock market predictions. The proposed paper describes how Cryptocurrency works, its use, legal prospect, security and what is the technology behind it
Virtual currencies or cryptocurrencies are based on Blockchain technology, also known as distributed ledger technology. As of March 2022, there are already over 10k virtual coins, their number being continuously growing since 2013. This paper aims to extract the public sentiment expressed towards the cryptocurrency market and Blockchain technology, two topics widely debated in the last decade. Our research was based on the use of Twitter data, collected with the help of an API in the RStudio environment.
With time-series data being prevalent everywhere, there is a need to predict this data accurately. This kind of data includes weather data, financial data such as stock price, and cryptocurrency price. Most of the trades in the stock market in this day and age are being made using artificial intelligence. An estimated 50% of trades were done using an algorithm, which increased to 60% in 2020 [1]. This highlights the demand for reliable and accurate predictions. The prediction of the price is very challenging. Some success has been seen when predicting stock prices, but not many studies have been done on cryptocurrency. Cryptocurrency, specifically Bitcoin, has seen a substantial increase in popularity, and the price has reflected this popularity. The price also follows patterns specifically when reaching new all-time highs. In this work, an Artificial intelligence is created and trained on the previous data to observe these patterns and predict the next price. The artificial intelligence chosen for this subject is Long short-term memory (LSTM). LSTMs are capable of finding patterns in time series data. LSTM solves the vanishing gradient problem present in the RNN (Recurrent Neural Network). The Market Price of Bitcoin is used as input here. The data values for input range from 20,000 up to 65,000 in testing. Once an optimal starting point is found, there is an 80/20 split of data, 80 percent of the data is used for training and 20 is used for testing. With the data being split, one of the most important jobs is figuring out the optimal lags (how far back into the past) when used to predict values. This range for this experiment is set to ten previous price days. Epochs (number of iterations) and Batch size (how much of the training data is used per epoch) are tested at different values to find optimal solutions. With batch size values such that batchSize ∈ {20, 21…26} and epochs such that epochs ∈ {10, 20….70}. Overfitting is hard to detect and thus can be an issue with too many epochs and smaller batch sizes (smaller means more of the training data is used). Too little and the LSTM will not learn the data patterns and thus will not have good accuracy. This is why different configurations are used in the experiment to maximize accuracy. This LSTM was used to achieve a Mean Absolute Percentage Error score of 3.23% and a Root Mean Squared Error score of 1892.87 when predicting next-day prices throughout 350.
Ashmit K. Khobragade, Omkar C. Keskar, Prathamesh G. Deshmukh, Rupali Chopade
Abstract: Bitcoin is a sort of cryptocurrency that has become a popular stock market investment. Many factors have an impact on the stock market. And bitcoin is a sort of cryptocurrency that has been slowly rising in recent years, with occasional severe declines that have had no discernible effect on the stock market. Because of the volatility, a prediction tool for bitcoin on the stock market is required. LSTM (Long Short-Term Memory) is a type of RNN module that was subsequently converted and used by numerous researchers, and it, like RNN, consists of recurrently consistent modules. The strategy and instruments we used to predict Bitcoin on the stock market yahoo finance can also be used to predict the price of cryptocurrencies. In the final section, we draw conclusions and discuss future work. Keywords: 1. LSTM., 2. Cryptocurrency., 3. Bitcoin. , 4. Prediction., 5. Machine Learning.
Cryptocurrencies are growing rapidly, with various altcoin being introduced recently, despite the fact that the market is very volatile, cryptocurrency now holds trillions of dollars in the market and has plenty of platforms for trading and owning cryptocurrencies, like Binance, Coinbase, and others. In particular, Bitcoin has caught the atten-tion of many people over the year with a current market cap. of 731.56 billion dollars circulating in the market. One of the major problems in cryptocurrencies is volatility, and often the prices can vary due to the external events that trigger the market. That is, Twitter sentiment. The objective of the article is to investigate people’s opinion about the cryptocurrency market on social media using collected tweets for 2 popular hashtags of Bitcoin and investigating the tweets using sentiment analysis. The study found that sentiment scores could be related to observed price fluctuations.
this study aims to analyze the impact of data selection to train machine learning models and forecast Bitcoin prices. Specifically, we train elastic net regularization models using two datasets with almost identical total observations. One dataset emphasizes years of observations (depth) over total variables, while the second one emphasizes the number of variables (width) over years of data. Our results suggest that the dataset with more extended historical time series and fewer variables provides a lower forecasting error than the dataset with shorter time series and more variables. Our results may be helpful to practitioners looking to identify data selection strategies to train ML-based forecasting models.
This paper proposes a two-stage approach to parametric nonlinear time series modelling in discrete time with the objective of incorporating uncertainty or misspecification in the conditional mean and volatility. At the first stage, a reference or approximating time series model is specified and estimated. At the second stage, Bayesian nonlinear expectations are introduced to incorporate model uncertainty or misspecification in prediction via specifying a family of alternative models. The Bayesian nonlinear expectations for prediction are constructed from closed-form Bayesian credible intervals evaluated using conjugate priors and residuals of the estimated approximating model. Using real Bitcoin data including some periods of Covid 19, applications of the proposed method to forecasting and risk evaluation of Bitcoin are discussed via three major parametric nonlinear time series models, namely the self-exciting threshold autoregressive model, the generalized autoregressive conditional heteroscedasticity model and the stochastic volatility model. Supplementary Information: The online version contains supplementary material available at 10.1007/s00181-022-02255-z.
Tamara Zuvela, Sara Lazarevic, Sofija Djordjevic, Marko Arsenović · 5 authors
Cryptocurrency is a type of digital or virtual currency that uses cryptography to secure and verify transactions as well as to control the creation of new units, it uses Blockchain properties for the same. Blockchain is a decentralized digital ledger technology that records transactions securely and transparently. Blockchain technology and cryptocurrency are closely connected. Cryptocurrencies rely on blockchain technology to operate, as blockchain serves as the decentralized ledger that records all transactions and ensures their security and transparency. [7] As the internet becomes more accessible and convenient, an increasing number of people and organizations are turning to digital transactions. Digital payment systems are significantly faster, less expensive, and more efficient. As a result, it's not unexpected that innovative digital payment system types are quickly emerging. No other approach even comes close to the colossus that is cryptocurrencies. Predicting cryptocurrency prices can be useful for a variety of reasons. For traders and investors, predicting cryptocurrency prices can help them make informed decisions about when to buy or sell cryptocurrencies, maximizing their profits or minimizing their losses. For prediction, the algorithms used are GRU (gated recurrent unit), LSTM (longshort-term memory), and Bi-LSTM (Bi-directional long-short-term memory) algorithms to predict the future price of a cryptocurrency. An ensemble model is also created using the three models, and prices could be accurately predicted using these models and displaying the obtained results.
Mohammed Mohassen Amanullah, Sainath Arjun, Kavisankar Leelasankar
Forums are online discussion sites where users can share ideas and post text messages to help. In other words, it's an area for people to talk via posted messages. NFTs (Non-Fungible Tokens) are data that are added to files that create unique signatures. It can be in image files, songs, tweets, text published on websites, physical objects, and various other digital formats. Essentially, this means that someone can own a digital file "and have it marked with a code to distinguish it from any digital copy". This application converts certain content in the forum which can be considered valuable and unique information into an NFT, with the consent of the user. In existing NFT trading platforms, an NFT creator can't be anyone. The creator has to be verified by the app and has to create NFTs according to the app specifications. Also, it becomes difficult to know whether the user is trustable or whether the content provided by the user is authentic or not. Therefore, an app is made where people of different interests come together and share their opinions/knowledge on a certain subject of a certain category where any valuable information is to be highlighted and the creator should be properly credited for the ownership of the information as an NFT.
We analyze the predictability of the bitcoin market across prediction horizons ranging from 1 to 60 min. In doing so, we test various machine learning models and find that, while all models outperform a random classifier, recurrent neural networks and gradient boosting classifiers are especially well-suited for the examined prediction tasks. We use a comprehensive feature set, including technical, blockchain-based, sentiment-/interest-based, and asset-based features. Our results show that technical features remain most relevant for most methods, followed by selected blockchain- based and sentiment-/interest-based features. Additionally, we find that predictability increases for longer prediction horizons. Although a quantile-based long-short trading strategy generates monthly returns of up to 39% before transaction costs, it leads to negative returns after taking transaction costs into account due to the particularly short holding periods. Cryptocurrencies, which the Bitcoin is the most remarkable one, have allured substantial awareness up to now, and they have encountered enormous instability in their price. While some studies utilize conventional statistical and econometric ways to uncover the driving variables of Bitcoin's prices, experimentation on the advancement of predicting models to be used as decision support tools in investment techniques is.
Cryptocurrency is a fascinating area of research developed due to the rapid development of financial technologies. One of the well-received cryptocurrencies is Bitcoin. The motivation behind this paper is to predict bitcoin prices with high accuracy using various regression-based models. Bitcoin is the fastest growing cryptocurrency. We have seen drastic changes in bitcoin prices over time. To make predictions for such changes, we use machine learning techniques over real-time data recorded for every 24-hour time interval since the presence of bitcoin beginning in the year 2009. We select eleven different regression models, analyze these models and obtain the best regression-based model for bitcoin price prediction. The results obtained from the study depict that the Bayesian ridge regressor outperforms all the other regression-based models followed by the Linear regressor.
Son dönemde para piyasalarında teknolojinin beraberinde getirdiği yeniliklerden dijital paralara ilgi artmaktadır. Gerek kaldıraçlı işlem yapılabilmesi gerek kısa sürede kazancı vadediyor oluşu, gerekse de alım-satım kolaylığı sebebiyle popülaritesi giderek artmaktadır. Bu çalışmada kripto paralar arasında en yüksek hacime sahip olması hasebiyle Bitcoin ve finansal değişkenlerden BIST100 endeksi arasındaki ilişkinin tespit edilmesi amaçlanmıştır. Bu doğrultuda 15.04.2011 ile 25.06.2021 tarihleri arası günlük veriler kullanılarak bu ilişki Eviews11 paket programında analiz edilmiştir. Bu amaçla analizin ilk aşamasında değişkenlerin birim kök içerip içermediği geleneksel birim kök testleri ile sınanmıştır. Daha sonra seriler arasında eşbütünleşme ilişkisini test etmek için Engel-Granger Eş Bütünleşme Analizi ve nedensellik testleri olarak Engel-Granger Nedensellik Testi, Toda-Yamamoto Nedensellik Testleri kullanılmıştır. Yapılan bu analizler ışığında eş bütünleşme testinin sonucuna göre Bitcoin-Bıst100 endeksi arasındaki ilişkinin eş bütünleşik olduğu tespit edilmiştir Engel-Granger Nedensellik testi BIST100 endeksinden Bitcoin fiyatlarına doğru iki yönlü nedensellik ilişkisi olduğunu doğrularken Toda-Yamamoto Nedensellik testi sonuçlarına göre ise Bıst100 endeksinden Bitcoin fiyatlarına doğru %5 anlamlılık düzeyinde anlamlı olduğu ve tek yönlü Toda-Yamamoto nedensellik ilişkisi görülmüştür. Son olarak çalışmanın sonuç bölümünde bütün bu bulgular önerilerle birlikte değerlendirilmiştir.
B. R. Rajakumar, B. R. Rajakumar, D. Binu, D. Binu · 6 authors
This paper introduces a new bitcoin predictin model that includes three major phases: data collection, Feature Extraction and Prediction. The initial phase is data collection, where Bitcoin raw data are collected, from which the features are extracted in the Features Extraction phase. The feature extraction is a noteworthy mechanism for detecting the bitcoin prices on day-by-day and minute-by –minute. Such that the indexed data collected are computed regarding certain standard indicators like Average True Range (ATR), Exponential Moving Average (EMA), Relative Strength Index (RSI) and Rate of Change (ROC). These technical indicators based features are subjected to prediction phase. As the major contribution, the prediction process is made precisely by deploying an improved DBN model, whose weights and activation function are fine-tuned using a new modified Lion Algorithm referred as Lion Algorithm with Adaptive Price Size (LAAPS). Finally, the performance of proposed work is compared and proved its superiority over other conventional models.
Cardano is an open-source and decentralized public blockchain platform, with consensus achieved using proof of stake. It can facilitate peer-to-peer transactions with its internal cryptocurrency, ADA, with no third-party involvement. In recent years, machine learning has been proliferating and has made many theoretical breakthroughs that find its application in many fields. The study of the machine learning approach in price prediction in Bitcoin and Ethereum has gained much attention, while relatively little research focuses on ADA forecasting. The experiment objective is to investigate the prediction of ADA's short period future prices dealing with real-world data. A comparative study of the results produced by different machine learning models, data visualizations, and statistical approaches. The experiment indicates that Gradient Boosting is the best-suited algorithm that can be selected to predict future ADA prices for short-term trading strategies.
Xinchen Zhang, Linghao Zhang, Qincheng Zhou, Xu Jin
As a result of the fast growth of financial technology and artificial intelligence around the world, quantitative algorithms are now being employed in many classic futures and stock trading, as well as hot digital currency trades, among other applications today. Using the historical price series of Bitcoin and gold from 9/11/2016 to 9/10/2021, we investigate an LSTM-P neural network model for predicting the values of Bitcoin and gold in this research. We first employ a noise reduction approach based on the wavelet transform to smooth the fluctuations of the price data, which has been shown to increase the accuracy of subsequent predictions. Second, we apply a wavelet transform to diminish the influence of high-frequency noise components on prices. Third, in the price prediction model, we develop an optimized LSTM prediction model (LSPM-P) and train it using historical price data for gold and Bitcoin to make accurate predictions. As a consequence of our model, we have a high degree of accuracy when projecting future pricing. In addition, our LSTM-P model outperforms both the conventional LSTM models and other time series forecasting models in terms of accuracy and precision.
Abstract Twitter sentiment has been shown to be useful in predicting whether Bitcoin’s price will increase or decrease. Yet the state-of-the-art is limited to predicting the price direction and not the magnitude of increase/decrease. In this paper, we seek to build on the state-of-the-art to not only predict the direction yet to also predict the magnitude of increase/decrease. We utilise not only sentiment extracted from tweets, but also the volume of tweets. We present results from experiments exploring the relation between sentiment and future price at different temporal granularities, with the goal of discovering the optimal time interval at which the sentiment expressed becomes a reliable indicator of price change. Two different neural network models are explored and evaluated, one based on recurrent nets and one based on convolutional networks. An additional model is presented to predict the magnitude of change, which is framed as a multi-class classification problem. It is shown that this model yields more reliable predictions when used alongside a price trend prediction model. The main research contribution from this paper is that we demonstrate that not only can price direction prediction be made but the magnitude in price change can be predicted with relative accuracy ( 63%).
Research on the prediction of cryptocurrency prices has been actively conducted, as cryptocurrencies have attracted considerable attention. Recently, researchers have aimed to improve the performance of price prediction methods by applying deep learning-based models. However, most studies have focused on predicting cryptocurrency prices for the following day. Therefore, clients are inconvenienced by the necessity of rapidly making complex decisions on actions that support maximizing their profit, such as “Sell”, “Buy”, and “Wait”. Furthermore, very few studies have explored the use of deep learning models to make recommendations for these actions, and the performance of such models remains low. Therefore, to solve these problems, we propose a deep learning model and three input features: sellProfit, buyProfit, and maxProfit. Through these concepts, clients are provided with criteria on which action would be most beneficial at a given current time. These criteria can be used as decision-making indices to facilitate profit maximization. To verify the effectiveness of the proposed method, daily price data of six representative cryptocurrencies were used to conduct an experiment. The results confirm that the proposed model showed approximately 13% to 21% improvement over existing methods and is statistically significant.
Sulalitha Bowala, Japjeet Singh, A. Thavaneswaran, Ruppa K. Thulasiram · 5 authors
Data-driven volatility models and neuro-volatility models have the potential to revolutionize the area of Computational Finance. Volatility measures the variation of a time series data, and thus it is also a driving factor for the risk forecasting of returns from investment in cryptocurrencies. A cryptocurrency is a decentralized medium of exchange that relies on cryptographic primitives to facilitate the trustless transfer of value between different parties. Instead of being physical money, cryptocurrency payments exist purely as digital entries on an online ledger called blockchain that describe specific transactions.Many commonly used risk forecasting models do not take into account the uncertainty associated with the volatility of an underlying asset to obtain the risk forecasts. Some tools from the fuzzy set theory can be incorporated into the forecasting models to account for this uncertainty. Interest in the use of hybrid models for fuzzy volatility forecasts is growing. However, a major drawback is that the fuzzy coefficient hybrid models used in fuzzy volatility forecasts are not data-driven. This paper uses fuzzy set theory with data-driven volatility and data-driven neuro-volatility forecasts to study the fuzzy risk forecasts. The study focuses on long-term volatility forecasts with daily price data while briefly exploring forecasting models with high-frequency (hourly) data as an avenue for future research. Simple yet effective models incorporating fuzziness to obtain fuzzy risk volatility forecasts and fuzzy VaR forecasts are presented. The key underlying idea, unlike the existing risk forecasting, is the use of a hybrid nonlinear adaptive fuzzy model for volatility.
Naveen Chakravarthy Sattaru, Dhananjay Umrao, K. K. Ramachandran, K. Karthick · 6 authors
In this current era, Machine Learning (ML) Approach is widely used as a predictive technology in transportation, finance, advertising, travel, healthcare, and various manufacturing industries across the globe. The modern-day financial market around the globe has experienced its deep impact on various aspects of digital pricing. Enormous organizations use numerous digital pricing techniques in order to generate maximum profit percentages for a sustainable future while conducting global business. On the other hand, the effective applications of the machine learning approach also offer relevant advantages in the Cryptocurrency Markets worldwide. It has been identified that with the use of ML approaches, organizations can conduct faster as well as cheaper transfers and exchange of money through virtual mediums easier than before. Moreover, Machine learning can easily improve all the trading strategies in the cryptocurrency and digital pricing markets for gaining more profit as well as adaptable business experience for future experiments. Researchers are going to investigate the particular research topic with an effective quantitative method by conducting secondary method as well as asking topic-related questions. In the modern share markets, undertaking numerous innovative ML technologies for enhancing efficiency in digital pricing and cryptocurrency has become easier. Therefore, the research paper sheds some important light on the impacts of ML approaches and their contributions in cryptocurrency trading and digital pricing for obtaining further research scopes.
Abstract As a new type of currency introduced in the new millennium, cryptocurrency has established its ecosystems and attracts many people to use and invest in it. However, cryptocurrencies are highly dynamic and volatile, making it challenging to predict their future values. In this research, we use a multivariate prediction approach and three different recurrent neural networks (RNNs), namely the long short-term memory (LSTM), the bidirectional LSTM (Bi-LSTM), and the gated recurrent unit (GRU). We also propose simple three layers deep networks architecture for the regression task in this study. From the experimental results on five major cryptocurrencies, i.e., Bitcoin (BTC), Ethereum (ETH), Cardano (ADA), Tether (USDT), and Binance Coin (BNB), we find that both Bi-LSTM and GRU have similar performance results in terms of accuracy. However, in terms of the execution time, both LSTM and GRU have similar results, where GRU is slightly better and has lower variation results on average.