Search results

Cryptocurrencies such as Bitcoin (BTC) attracted a lot of attention in recent months due to their unprecedented price fluctuations. This paper aims to propose a new method for predicting the direction of BTC price using linear discriminant analysis (LDA) together with sentiment analysis.

Concretely, the authors train an LDA-based classifier that uses the current BTC price information and BTC news announcements headlines to forecast the next-day direction of BTC prices. The authors compare the results with a Support Vector Machine (SVM) model and random guess approach. The use of BTC price information and news announcements related to crypto enables us to value the importance of these different sources and types of information.

Relative to the LDA results, the SVM model was more accurate in predicting BTC next day’s price movement. All models yielded better forecasts of an increase in tomorrow’s BTC price compared to forecasting a decrease in the crypto price. The inclusion of news sentiment resulted in the highest forecast accuracy of 0.585 on the test data, which is superior to a random guess. The LDA (SVM) model with asset specific (news sentiment and asset specific) input features ranked first within their respective model classifiers, suggesting both BTC news sentiment and asset specific are prized factors in predicting tomorrow’s price direction.

To the best of the authors’ knowledge, this is the first study to analyze the potential effect of crypto-related sentiment and BTC specific news on BTC’s price using LDA and sentiment analysis.

The purpose of this paper is to shed fresh light into whether an energy commodity price index (ENFX) and energy blockchain-based crypto price index (ENCX) can be used to predict movements in the energy commodity and energy crypto market.

Using principal component analysis over daily data of crude oil, heating oil, natural gas and energy based cryptos, the ENFX and ENCX indices are constructed, where ENFX (ENCX) represents 94% (88%) of variability in energy commodity (energy crypto) prices.

Natural gas price movements were better explained by ENCX, and shared positive (negative) correlations with cryptos (crude oil and heating oil). Using a vector autoregressive model (VAR), while the 1-day lagged ENCX (ENFX) was significant in estimating current ENCX (ENFX) values, only lagged ENCX was significant in estimating current ENFX. Granger causality tests confirmed the two markets do not granger cause each other. One standard deviation shock in ENFX had a negative effect on ENCX. Weak forecasting results of the VAR model, support the two markets are not robust forecasters of each other. Robustness wise, the VAR model ranked lower than an autoregressive model, but higher than a random walk model.

Significant structural breaks at distinct dates in the two markets reinforce that the two markets do not help to predict each other. The findings are limited by the existence of bubbles (December 2017-January 2018) which were witnessed in energy blockchain-based crypto markets and natural gas, but not in crude oil and heating oil.

As per the authors’ knowledge, this is the first paper to analyze the relationship between leading energy commodities and energy blockchain-based crypto markets.

This paper aims to investigate the implementation of the short selling ban policy imposed by the Italian stock exchange on health-care stock prices, as a tool to mitigate COVID-19 price effects. Important contributions are in terms of assessing the effect of the temporary short selling ban on restricted health-care stocks; the effect of COVID-19 cases and crude oil price volatility onto health-care stocks; and whether COVID-19 resulted in a change in the risk and average stock price of health-care stocks.

The methodology involves impulse responses to capture the shock of the short selling ban onto health-care stocks, and Markov switching regimes to capture the effect of COVID-19 onto the risk and prices in the health-care industry. Daily data from 9 November 2018 till 23 December 2020 is used.

Findings suggest there were significant changes in average prices in health-care technology and health-care services stocks before, during and after the short selling ban. Shocks to the number of COVID-19 cases and crude oil price volatility impacted health-care stocks but lasted only for a few days. While daily changes in the number of COVID-19 cases impacted some health-care stocks in the presence of a two-state Markov regime, insignificant coefficients and relatively low duration suggest that the short selling policy did not significantly change the average price and risk in health-care stocks to explain a two-state regime in the health-care industry.

Insignificant coefficients in a two-state Markov regime reinforce that short-selling policies have a short-lasting effect onto health-care equity prices. The findings are limited by the duration of the short selling policy, the pandemic event and the health-care industry.

This is the first study to look at the impact of early COVID-19 and short selling ban policy on health-care stocks.

This paper aims to investigate the role of price-based information from major cryptocurrencies, foreign exchange, equity markets and key commodities in predicting the next-minute Bitcoin (BTC) price. This study answers the following research questions: What is the best sparse regression model to predict the next-minute price of BTC? What are the key drivers of the BTC price in high-frequency trading?

Least absolute shrinkage and selection operator and Ridge regressions are adopted using minute-based open-high-low-close prices, volume and trade count for eight major cryptos, global stock market indices, foreign currency pairs, crude oil and gold price information for February 2020–March 2021. This study also examines whether there was any significant break and how the accuracy of the selected models was impacted.

Findings suggest that Ridge regression is the most effective model for predicting next-minute BTC prices based on BTC-related covariates such as BTC-open, BTC-high and BTC-low, with a moderate amount of regularization. While BTC-based covariates BTC-open and BTC-low were most significant in predicting BTC closing prices during stable periods, BTC-open and BTC-high were most important during volatile periods. Overall findings suggest that BTC’s price information is the most helpful to predict its next-minute closing price after considering various other asset classes’ price information.

To the best of the authors’ knowledge, this is the first paper to identify the covariates of major cryptocurrencies and predict the next-minute BTC crypto price, with a focus on both crypto-asset and cross-market information.