Search

Cryptocurrencies, such as Bitcoin, are one of the most controversial and complex technological innovations in today's financial system. This study aims to forecast the movements of Bitcoin prices at a high degree of accuracy. To this aim, four different Machine Learning (ML) algorithms are applied, namely, the Support Vector Machines (SVM), the Artificial Neural Network (ANN), the Naive Bayes (NB) and the Random Forest (RF) besides the logistic regression (LR) as a benchmark model. In order to test these algorithms, besides existing continuous dataset, discrete dataset was also created and used. For the evaluations of algorithm performances, the F statistic, accuracy statistic, the Mean Absolute Error (MAE), the Root Mean Square Error (RMSE) and the Root Absolute Error (RAE) metrics were used. The t test was used to compare the performances of the SVM, ANN, NB and RF with the performance of the LR. Empirical findings reveal that, while the RF has the highest forecasting performance in the continuous dataset, the NB has the lowest. On the other hand, while the ANN has the highest and the NB the lowest performance in the discrete dataset. Furthermore, the discrete dataset improves the overall forecasting performance in all algorithms (models) estimated., Comment: 14 pages, 2 figures and 15 tables

This study examines the impacts of US and China trade policy uncertainties on the US’s commodity level bilateral trade balances (henceforth, BTBs) with China. To this end, newly created trade polic...

This paper investigates the dynamic causalities between economic growth, financial development, international trade, tourism expenditure and/on the CO2 emissions in Greece over the period of 1970–2014. For this purpose, the Zivot-Andrews unit root tests and the Autoregressive-Distributed Lag (ARDL) models were applied. The Vector Error Correction Model (VECM) and the robustness of causality test results indicate that Greece’s economic growth, financial development, international trade, tourism expenditures, and CO2 emissions are co-integrated in the long run. The empirical findings show that economic growth, financial development, international trade, and tourism expenditures caused increases in Greece’s CO2 emissions. It should be noted that tourism, as a leading sector in the Greek economy, has serious negative environmental impacts for Greece in the long run. Therefore, the policy makers of Greece should strongly take into consideration this threat from the tourism sector as the whole Greek eco...

WOS: 000464854500035, PubMed ID: 30778930, This study aims to test the EKC (Environmental Kuznets Curve) hypothesis for the ten states, having the highest levels of carbon dioxide emissions in the USA, through the independent variables of real GDP, population, and renewable energy and fossil energy consumptions. To this aim, the panel estimation method with cross-sectional dependence is applied to data from 1980 to 2015. The empirical findings of the study indicate that the EKC (inverted U-shaped) hypothesis is valid only for Florida, Illinois, Michigan, New York, and Ohio. Interestingly, the negative impacts of fossil energy consumption on CO2 emission levels in Texas are not detected statistically although this state is the leading oil-producing state. Furthermore, the positive impacts of renewable energy consumption in Florida, officially known as "Sunshine State", are considerably low when compared with the other states.

This study investigates the validity of the EKC (environmental Kuznets curve) hypothesis for the 50 US states and a Federal District (Washington, D.C.). To this aim, the common correlated effects (CCE) and the augmented mean group (AMG) estimation procedures are applied between 1980 and 2015. While the CCE estimation does not support EKC hypothesis, the AMG does. The empirical findings of the AMG estimation indicate that only 14 states verify the EKC hypothesis. Additionally, the expected negative impacts of fossil energy consumption on the environment (CO2 emissions) are strongly detected in all states except Texas. However, the expected positive impacts of renewable energy consumption on the CO2 emissions are detected only in 13 states. Furthermore, the expected negative impacts of the population are not detected in some mostly populated states like New York, Texas, and Ohio. The overall findings of this study may help the US state-level policy makers in two ways: first, to understand whether their economic growths are sustainable (eco-friendly); second, to see how their fossil and renewable energy consumptions affect their environments and to review their energy policies.