In this article we forecast daily closing price series of Bitcoin, Litecoin and Ethereum cryptocurrencies, using data on prices and volumes of prior days. Cryptocurrencies price behaviour is still largely unexplored, presenting new opportunities for researchers and economists to highlight similarities and differences with standard financial prices. We compared our results with various benchmarks: one recent work on Bitcoin prices forecasting that follows different approaches, a well-known paper that uses Intel, National Bank shares and Microsoft daily NASDAQ closing prices spanning a 3-year interval and another, more recent paper which gives quantitative results on stock market index predictions. We followed different approaches in parallel, implementing both statistical techniques and machine learning algorithms: the Simple Linear Regression (SLR) model for uni-variate series forecast using only closing prices, and the Multiple Linear Regression (MLR) model for multivariate series using both price and volume data. We used two artificial neural networks as well: Multilayer Perceptron (MLP) and Long short-term memory (LSTM). While the entire time series resulted to be indistinguishable from a random walk, the partitioning of datasets into shorter sequences, representing different price “regimes”, allows to obtain precise forecast as evaluated in terms of Mean Absolute Percentage Error(MAPE) and relative Root Mean Square Error (relativeRMSE). In this case the best results are obtained using more than one previous price, thus confirming the existence of time regimes different from random walks. Our models perform well also in terms of time complexity, and provide overall results better than those obtained in the benchmark studies, improving the state-of-the-art.
The network of developers in distributed ledgers and blockchains open source projects is essential to maintaining the platform: understanding the structure of their exchanges, analysing their activity and its quality (e.g. issues resolution times, politeness in comments) is important to determine how "healthy" and efficient a project is. The quality of a project affects the trust in the platform, and therefore the value of the digital tokens exchanged over it. In this paper, we investigate whether developers' emotions can effectively provide insights that can improve the prediction of the price of tokens. We consider developers' comments and activity for two major blockchain projects, namely Ethereum and Bitcoin, extracted from Github. We measure sentiment and emotions (joy, love, anger, etc.) of the developers' comments over time, and test the corresponding time series (i.e. the affect time series) for correlations and causality with the Bitcoin/Ethereum time series of prices. Our analysis shows the existence of a Granger-causality between the time series of developers' emotions and Bitcoin/Ethereum price. Moreover, using an artificial recurrent neural network (LSTM), we can show that the Root Mean Square Error (RMSE)-associated with the prediction of the prices of cryptocurrencies-significantly decreases when including the affect time series.
This paper studies how to forecast daily closing price series of Bitcoin, using data on prices and volumes of prior days. Bitcoin price behaviour is still largely unexplored, presenting new opportunities. We compared our results with two modern works on Bitcoin prices forecasting and with a wellknown recent paper that uses Intel, National Bank shares and Microsoft daily NASDAQ closing prices spanning a 3-year interval. We followed different approaches in parallel, implementing both statistical techniques and machine learning algorithms. The SLR model for univariate series forecast uses only closing prices, whereas the MLR model for multivariate series uses both price and volume data. We applied the ADF -Test to these series, which resulted to be indistinguishable from a random walk. We also used two artificial neural networks: MLP and LSTM. We then partitioned the dataset into shorter sequences, representing different price "regimes", obtaining best result using more than one previous price, thus confirming our regime hypothesis. All the models were evaluated in terms of MAPE and relativeRMSE. They performed well, and were overall better than those obtained in the benchmarks. Based on the results, it was possible to demonstrate the efficacy of the proposed methodology and its contribution to the state-of-the-art.
We introduce a model of noncommutative geometry that gives rise to the uncertainty relations recently derived from the discussion of a quantum clock. We investigate the dynamics of a free particle in this model from the point of view of doubly special relativity and discuss the geodesic motion in a Schwarzschild
Composite materials provide many advantages over more conventional materials. However, their susceptibility to impact damage can question their use in critical load-bearing structures, and efficient methods are needed for early damage detection. To this purpose, the nonlinear vibro-acoustic modulation (VAM) technique applies a low-frequency pump excitation and a high-frequency probe excitation to exploit the onset of harmonic components around the probe frequency of the damaged structural response. The VAM technique has been widely studied on structures instrumented with piezoceramic transducers used for both actuation and sensing, but few attempts have been made to use equipment typical of modal testing, such as shakers and accelerometers. In this study, the VAM technique is applied to a composite laminate beam by employing an electro-dynamic shaker to generate low-frequency flexural excitation, a low-profile piezoceramic transducer to introduce the probe wave, and a micro-accelerometer to sense the structural response. Three resonance low frequencies and two acoustic frequencies are considered in different testing scenarios, at increasing levels of excitation amplitude. The results show a general good performance of the technique with the adopted experimental setup, the choice of the probe frequency and the higher level of the pump excitation having a significant impact on its sensitivity.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.