Objetivo: Presentar tres alternativas para el diseño de un sistema difuso, con la intención de predecir la señal precio del Bitcoin (BTC) en dólares (USD). Metodología: Se realizó un análisis matemático y grafico de la señal del precio del Bitcoin [BTC]. Los datos de entrada se han seleccionado como precios de cierre para cada periodo, donde el periodo es constante y de 30 minutos. Con esto se busca identificar posibles características de interés, patrones periódicos o presencia de ruido. Resultados: En la primera aproximación a la solución del problema, se construyó un sistema difuso con motor de inferencia Mamdani en el que los parámetros de la máquina se ajustan manualmente, basándose en los patrones encontrados en el estudio previo de la señal y en el conocimiento de un experto en el área. La segunda solución se generó mediante el algoritmo ANFIS, que realiza el ajuste automático de los parámetros empleando algoritmos de gradiente descendiente; y la tercera solución se diseñó a través de la implementación de un algoritmo bioinspirado, conocido como algoritmo genético simple. Conclusiones: En los tres casos, son cinco las entradas del sistema, cada una de las cuales corresponde a muestras de la señal del precio; la salida, por su parte, es la predicción del precio para el periodo siguiente.
Jan 1, 2019·2019 Joint International Conference on Digital Arts, Media and Technology with ECTI Northern Section Conference on Electrical, Electronics, Computer and Telecommunications Engineering (ECTI DAMT-NCON)
This research represents a model of buying and selling lotteries system on Blockchain by using Ethereum network to determines the conditions for the purchasing of the lottery and reward the prize winner. Our system uses Ethereum coins to buy and reward the prize for convenience in term of speed and also reduce the problems which is unable to be controlled by the government. For example, lottery agents (intermediaries) may sell the lottery at overprice, and reward the winners at a lower than appropriate rate. Additionally, the most important problem is the verification of the real owner of the lottery.
Aleš Zamuda, Vincenzo Crescimanna, Juan C. Burguillo, Joana Dias · 12 authors
This chapter surveys the state-of-the-art in forecasting cryptocurrency value by Sentiment Analysis. Key compounding perspectives of current challenges are addressed, including blockchains, data collection, annotation, and filtering, and sentiment analysis metrics using data streams and cloud platforms. We have explored the domain based on this problem-solving metric perspective, i.e., as technical analysis, forecasting, and estimation using a standardized ledger-based technology. The envisioned tools based on forecasting are then suggested, i.e., ranking Initial Coin Offering (ICO) values for incoming cryptocurrencies, trading strategies employing the new Sentiment Analysis metrics, and risk aversion in cryptocurrencies trading through a multi-objective portfolio selection. Our perspective is rationalized on the perspective on elastic demand of computational resources for cloud infrastructures.
Paulo Vítor Jordão da Gama Silva, Marcelo Cabús Klötzle, Antônio Carlos Figueiredo Pinto, Leonardo Lima Gomes
In the 21st century, digital currencies have become a disruptive technology that is shaking up both financial markets and academic environment. Investors, politicians, companies, and academics are attempting to improve their understanding of these currencies for future investment possibilities and technological applications. This study aims to evaluate changes in different volatility states of eight digital currencies (BTC, ETH, LTC, XRP, XMR, NEM, LISK, and STEEM) that showed the highest liquidity and market capitalisation from 2013 to 2017. The methodology involved the MSGARCH model, using SGARCH, EGARCH, GJRGARCH, and TGARCH models. Our study demonstrated that two volatility regimes, that is, one with a larger volatility and another with a smaller one, clearly exist for all the analysed cryptocurrencies. What differs between the currencies is the probability of a second regime occurring. Moreover, we concluded that for both the first and second state, the asymmetry coefficient (gamma) is positive for all currencies.
This study assessed the volatility and the Value at Risk (VaR) of daily returns of Bitcoins by conducting a comparative study in the forecast performance of symmetric and asymmetric GARCH models based on three different error distributions. The models employed are the SGARCH and TGARCH which were validated based on AIC, MAE and MSE measures. The results indicated that the SGARCHGED (1,1) with generalised error distribution term was identified as the best fitted GARCH model. Though, this best fitted model based on information loss (AIC) did not provide the best out-of-sample forecast, the differences was insignificant. Thus, the study clearly demonstrates that it is reliable to use the best fitted model for volatility forecasting. Also, to further validate the performance of the best fitted model, it was subjected to a historical back-test using Value at Risk (VaR). Though, it was evident from the study that no model was superior, it was indicated that an average loss of 1.2% is expected to be exceeded only 1% of the time. Moreover, volatility forecast from the back testing was relatively high during the first quarter of 2018 but begun decreasing steadily with time.
Daniel Traian Pele, Niels Wesselhöfft, Wolfgang Karl Härdle, Michalis Kolossiatis · 5 authors
The aim of this paper is to prove the phenotypic convergence of cryptocurrencies, in the sense that individual cryptocurrencies respond to similar selection pressures by developing similar characteristics. In order to retrieve the cryptocurrencies phenotype, we treat cryptocurrencies as financial instruments (genus proximum) and find their specific difference (differentia specifica) by using the daily time series of log-returns. In this sense, a daily time series of asset returns (either cryptocurrencies or classical assets) can be characterized by a multidimensional vector with statistical components like volatility, skewness, kurtosis, tail probability, quantiles, conditional tail expectation or fractal dimension. By using dimension reduction techniques (Factor Analysis) and classification models (Binary Logistic Regression, Discriminant Analysis, Support Vector Machines, K-means clustering, Variance Components Split methods) for a representative sample of cryptocurrencies, stocks, exchange rates and commodities, we are able to classify cryptocurrencies as a new asset class with unique features in the tails of the log-returns distribution. The main result of our paper is the complete separation of the cryptocurrencies from the other type of assets, by using the Maximum Variance Components Split method. More, we observe a divergent evolution of the cryptocurrencies species, compared to the classical assets, mainly due to the tails behaviour of the log-returns distribution. The codes used here are available via www.quantlet.de.
In recent years, deep learning has been widely used for time series prediction. Deep learning model that is most often used for time series prediction is LSTM. LSTM is widely used because of its excellence in remembering very long sequences. However, doing training on models that use LSTM requires a long time. Trying from one model to another model that use LSTM will take a very long time, thus a method is needed for optimizing hyperparameter to get a model with a small RMSE. This research proposed Artificial Bee Colony (ABC) as a method in optimizing hyperparameter for models that use LSTM. ABC is a metaheuristic method that mimics the behavior of bee colonies in foraging. Optimized hyperparameter in this research consisted of sliding window size, number of LSTM units, dropout rate, regularizer, regularizer rate, optimizer and learning rate. In this research the proposed method called as ABC-LSTM. Bitcoin prices historical data was used as the dataset for evaluating the prediction of the models. The best ABC-LSTM model resulted best RMSE of 189.61 compared to model that use LSTM without optimization resulted best RMSE of 236.17. This result showed that ABC-LSTM model outperformed models that use LSTM without optimization.
This study examines and compares the volatility in sample fit and out of sample forecast of four different heteroscedasticity models, namely ARCH, GARCH, EGARCH and GJR-GARCH applied to Bitcoin, Ethereum and Ripple. The models are fitted over the period from 2016-01-01 to 2019-01-01 and then used to obtain one day rolling forecasts during the period from 2018-01-01 to 2019-01-01. The study investigates three different themes consisting of the modelling framework structure, complexity of models and the relation between a good in sample fit and good out of sample forecast. AIC and BIC are used to evaluate the in sample fit while MSE, MAE and R2LOG are used as loss functions when evaluating the out of sample forecast against the chosen Parkinson volatility proxy. The results show that a heavier tailed reference distribution than the normal distribution generally improves the in sample fit, while this generality is not found for the out of sample forecast. Furthermore, it is shown that GARCH type models clearly outperform ARCH models in both in sample fit and out of sample forecast. For Ethereum, it is shown that the best fitted models also result in the best out of sample forecast for all loss functions, while for Bitcoin non of the best fitted models result in the best out of sample forecast. Finally, for Ripple, no generality between in sample fit and out of sample forecast is found.
In early 2018 prices peaked at USD 20,000 and, almost two years later, we still continue debating if cryptocurrencies can actually become a currency for the everyday life or not. From the economic point of view, and playing in the field of behavioral finance, this paper analyses the relation between prices and the search interest on Bitcoin since 2014. We questioned the forecasting ability of Google Trends for the behavior of price by performing linear and nonlinear dependency tests, and exploring performance of ARIMA and Neural Network models enhanced with this social sentiment indicator. Our analyses and models are founded upon a set of statistical properties common to financial returns that we establish for Bitcoin, Ethereum, Ripple and Litecoin.
The electronic transition has been gaining a large groundin recent decades due to the use of crypto currencies. One of the most popular is Bitcoin. It is open source, the transactions and the issuance of bitcoins occur collectively through the network.The analysis of the behavior of Bitcoin becomes a relevance to the prediction Price and achieve successful investments in it.This review is conducted for the analysis and comparison of the of the different prediction methods focused on the bitcoin price. Anemphasis is placed on those who have a structure as the basis of the ARIMA model, then adding to the hybrid methods, which use neural networks to complete the method.
With the growing interest in cryptocurrency and its algorithm, studies on cryptocurrency price predations have been extensively conducted in various academic disciplines. Since the cryptocurrency is generated and consumed by the Blockchain system, it has been considered that Blockchain-specific information would be the main components in predicting cryptocurrency prices. Specifically, this point of view has been largely employed in the studies of Bitcoin price predictions. However, this study recognizes that Ethereum, a popular and leading cryptocurrency in the market, has distinct Blockchain information as compared to that of Bitcoin. We attempt to investigate the relationships between inherent Ethereum Blockchain information and Ethereum prices. Furthermore, the research examines how Blockchain information of other coins in the market is associated with Ethereum prices. The results of data analysis show that Ethereum Blockchain information and Blockchain information of other coins have strong correlations with the final Ethereum prices.
Realized volatility (RV) is defined as the sum of the squares of logarithmic returns on high-frequency sampling grid and aggregated over a certain time interval, typically a trading day in finance. It is not a priori clear what the aggregation period should be in case of continuously traded cryptocurrencies at online exchanges. In this work, we aggregate RV values using minute-sampled Bitcoin returns over 3-h intervals. Next, using the RV time series, we predict the future values based on the past samples using a plethora of machine learning methods, ANN (MLP, GRU, LSTM), SVM, and Ridge Regression, which are compared to the Heterogeneous Auto-Regressive Realized Volatility (HARRV) model with optimized lag parameters. It is shown that Ridge Regression performs the best, which supports the auto-regressive dynamics postulated by HARRV model. Mean Squared Error values by the neural-network based methods closely follow, whereas the SVM shows the worst performance. The present benchmarks can be used for dynamic risk hedging in algorithmic trading at cryptocurrency markets.
The objective of this paper is to simulate the trading of the currency pair BTC/USD, investigating through the theory of the genetic algorithms the best sets of trading strategies, simulating through a realistic order book the bitcoin price formation, and reproducing a bitcoin price series that exhibits some stylized facts found in real-time price series. In this artificial market model two kinds of agents, Chartists and Random traders, perform trading. Chartists trade through the application of trading rules. Specifically, a part of Chartists trades applying the best sets of trading rules selected by a genetic algorithm that simulates a trading system, based on four technical analysis indicators, searching for parameters of each indicator that guarantee the highest profits in the training period; the remaining part trades applying trading rules choosing their parameters in a random way. On the contrary random trader's trade without applying any trading strategy, issuing in a random way sell or buy orders. Results show that the best sets of rules found to guarantee the highest profits both in the training and in the testing periods, and perform well also in the artificial market model where the Chartists who adopt the best sets of trading rules are able to achieve higher profits.
Nor Azizah Hitam, Amelia Ritahani Ismail, Faisal Saeed
Forecasting accurate future price is very important in financial sector. An optimized Support Vector Machine (SVM) based on Particle Swarm Optimization (PSO) is introduced in forecasting the cryptocurrency future price. It is part of Artificial Intelligence (AI) that uses previous experience to forecast future price. Analysts and investors generally combine fundamental and technical analysis prior to decide the best price to execute their trades. Some may use Machine Learning Algorithms to execute their trades. However, forecasting result using basic SVM algorithms does not really promising. On the other hands, Particle Swarm Optimization (PSO) is known as a better algorithm for a static and simple optimization problem. Therefore, PSO is introduced to optimize the algorithms of SVM in cryptocurrency forecasting. The experiment of selected cryptocurrencies is conducted for this classifier. The experimental result demonstrates that an optimized SVM-PSO algorithm can effectively forecast the future price of cryptocurrency thus outperforms the single SVM algorithms.
Cryptocurrencies lack clear measures of fundamental values and are often associated with speculative bubbles. This paper introduces a new way of testing for speculative bubbles based on StockTwits sentiment, which is used as the transition variable in a smooth transition autoregression. The model allows for conditional heteroskedasticity and fat tails of the conditional distribution of the error term, and volatility may depend on the constructed sentiment index. We apply the model to the CRIX index, for which several bubble periods are identified. The detected locally explosive price dynamics, given the specified bubble regime controlled by a smooth transition function, are more akin to the notion of speculative bubble that is driven by exuberant sentiment. Furthermore, we find that volatility increases as the sentiment index decreases, which is analogous to the commonly called leverage effect.