Research

Jump to: Review, Other

Open AccessArticle

Pump It: Twitter Sentiment Analysis for Cryptocurrency Price Prediction

by

Vladyslav Koltun

and

Ivan P. Yamshchikov

Risks 2023, 11(9), 159; https://doi.org/10.3390/risks11090159 - 04 Sep 2023

Viewed by 429

Abstract

This study demonstrates the significant impact of market sentiment, derived from social media, on the daily price prediction of cryptocurrencies in both bull and bear markets. Through the analysis of approximately 567 thousand tweets related to twelve specific cryptocurrencies, we incorporate the sentiment [...] Read more.

This study demonstrates the significant impact of market sentiment, derived from social media, on the daily price prediction of cryptocurrencies in both bull and bear markets. Through the analysis of approximately 567 thousand tweets related to twelve specific cryptocurrencies, we incorporate the sentiment extracted from these tweets along with daily price data into our prediction models. We test various algorithms, including ordinary least squares regression, long short-term memory network and neural hierarchical interpolation for time series forecasting (NHITS). All models show better performance once the sentiment is incorporated into the training data. Beyond merely assessing prediction error, we scrutinise the model performances in a practical setting by applying them to a basic trading algorithm managing three distinct portfolios: established tokens, emerging tokens, and meme tokens. While NHITS emerged as the top-performing model in terms of prediction error, its ability to generate returns is not as compelling. Full article

(This article belongs to the Special Issue Cryptocurrencies and Risk Management)

► Show Figures

Figure 1

Open AccessEditor’s ChoiceArticle

Cryptocurrency Risks, Fraud Cases, and Financial Performance

by

David S. Kerr

,

Karen A. Loveland

,

Katherine Taken Smith

and

Lawrence Murphy Smith

Risks 2023, 11(3), 51; https://doi.org/10.3390/risks11030051 - 23 Feb 2023

Cited by 3 | Viewed by 3415

Abstract

In this study, we examine major cryptocurrencies, present notable fraud cases, describe fraud risks, and analyze cryptocurrency financial performance. People debate whether cryptocurrency is an investment opportunity, the new Dutch Tulip Bubble, or a giant Ponzi scheme. There have been a number of [...] Read more.

In this study, we examine major cryptocurrencies, present notable fraud cases, describe fraud risks, and analyze cryptocurrency financial performance. People debate whether cryptocurrency is an investment opportunity, the new Dutch Tulip Bubble, or a giant Ponzi scheme. There have been a number of high-profile fraud cases associated with cryptocurrencies, such as the FTX scandal in late 2022, thereby making fraud a real concern to current and potential future investors. Regarding financial performance, cryptocurrencies experienced a major collapse in value in the most recent period of the study, about three times worse than the major stock market indices. While in prior periods, cryptocurrencies have significantly outperformed stock market indices, recent fraud cases and the extreme volatility of cryptocurrencies indicate that investing in cryptocurrencies comes with much higher risk than traditional stock market investments. The debate over the investment potential of cryptocurrencies continues, whether they have long term value or are simply the new Dutch Tulip Bubble. The study’s findings will be useful to investors, regulators, and academic researchers regarding the cryptocurrency industry. Full article

(This article belongs to the Special Issue Cryptocurrencies and Risk Management)

Open AccessArticle

Forecasting Bitcoin Volatility Using Hybrid GARCH Models with Machine Learning

by

Mamoona Zahid

,

Farhat Iqbal

and

Dimitrios Koutmos

Risks 2022, 10(12), 237; https://doi.org/10.3390/risks10120237 - 13 Dec 2022

Cited by 1 | Viewed by 2746

Abstract

The time series movements of Bitcoin prices are commonly characterized as highly nonlinear and volatile in nature across economic periods, when compared to the characteristics of traditional asset classes, such as equities and commodities. From a risk management perspective, such behaviors pose challenges, [...] Read more.

The time series movements of Bitcoin prices are commonly characterized as highly nonlinear and volatile in nature across economic periods, when compared to the characteristics of traditional asset classes, such as equities and commodities. From a risk management perspective, such behaviors pose challenges, given the difficulty in quantifying and modeling Bitcoin’s price volatility. In this study, we propose hybrid analytical techniques that combine the strengths of the non-stationary properties of Generalized Autoregressive Conditional Heteroskedasticity (GARCH) models with the nonlinear modeling capabilities of deep learning algorithms, such as Long Short-Term Memory (LSTM), Gated Recurrent Unit (GRU), and Bidirectional LSTM (BiLSTM) algorithms with single, double, and triple layer network architectures to forecast Bitcoin’s realized price volatility. Our findings, both in-sample and out-of-sample, show that such hybrid models can generate accurate forecasts of Bitcoin’s price volatility. Full article

(This article belongs to the Special Issue Cryptocurrencies and Risk Management)

► Show Figures

Figure 1

Open AccessArticle

Expectations of Macroeconomic News Announcements: Bitcoin vs. Traditional Assets

by

Ivan Mužić

and

Ivan Gržeta

Risks 2022, 10(6), 123; https://doi.org/10.3390/risks10060123 - 12 Jun 2022

Cited by 3 | Viewed by 2003

Abstract

Research on cryptocurrencies has proliferated in recent years. Our research objective was to answer the question of whether macroeconomic news from the U.S. affects Bitcoin in the same way it affects other common investment assets such as gold, the S&P 500, 2-year Treasury [...] Read more.

Research on cryptocurrencies has proliferated in recent years. Our research objective was to answer the question of whether macroeconomic news from the U.S. affects Bitcoin in the same way it affects other common investment assets such as gold, the S&P 500, 2-year Treasury bills, and 10-year Treasury bills. Following previous research, seven macroeconomic news announcements from the U.S. were selected, and an empirical analysis of the daily returns, volatility, and volume of the selected assets was conducted. The results show that while Bitcoin is the most volatile (i.e., riskiest) of all the assets, the expected direction of movement is visible after the official announcement of the macroeconomic news on that day, and is comparable to that of the 2-year Treasury bills. It is also evident that the trading volume of Bitcoin does not change, unlike other assets, suggesting that the price of Bitcoin is always moved by the same players, indicating the closed and, therefore, riskier nature of cryptocurrency markets. Finally, we found evidence that the impact of macroeconomic announcements on Bitcoin returns is stronger when the announcements are negative but, interestingly, the returns of Bitcoin, unlike those of other assets, are more volatile after positive announcements. Full article

(This article belongs to the Special Issue Cryptocurrencies and Risk Management)

Open AccessArticle

Cryptocurrency as an Investment: The Malaysian Context

by

Shangeetha Sukumaran

,

Thai Siew Bee

and

Shaista Wasiuzzaman

Risks 2022, 10(4), 86; https://doi.org/10.3390/risks10040086 - 14 Apr 2022

Cited by 9 | Viewed by 11277

Abstract

Cryptocurrency is gaining popularity worldwide, with some countries already starting to regulate and accept cryptocurrency in their financial services. Malaysia’s Securities Commission (SC) announced in October 2021 that over MYR 16 billion (USD 3.85 billion) involving digital assets and cryptocurrencies were traded between [...] Read more.

Cryptocurrency is gaining popularity worldwide, with some countries already starting to regulate and accept cryptocurrency in their financial services. Malaysia’s Securities Commission (SC) announced in October 2021 that over MYR 16 billion (USD 3.85 billion) involving digital assets and cryptocurrencies were traded between August 2020 and September 2021. Since cryptocurrencies are issued by private corporations and are technically beyond the federal government’s control, criminals may use them for illegal reasons such as money laundering and terrorist funding. Consequently, it is vital to examine why investors are engaged in cryptocurrency in the first place. This study aims to provide insight into Malaysian investors’ perceptions by evaluating the influence of perceived risk and perceived value on their cryptocurrency adoption decision. The retail investors’ demographic characteristics (gender, age, education, income, and investment experience) were analyzed as control variables. Data were gathered using purposive sampling, and responses from 211 respondents from various cities in Malaysia were used in the final analysis. Data were examined using Smart PLS Structural Equation Modelling (PLS-SEM). Based on the finding’s, perceived value was found to have a significant influence on cryptocurrency adoption. Meanwhile, perceived risk had no significant influence on the adoption of cryptocurrency among the Malaysian investors. Full article

(This article belongs to the Special Issue Cryptocurrencies and Risk Management)

► Show Figures

Figure 1

Open AccessArticle

Does Cryptocurrency Hurt African Firms?

by

Mina Sami

and

Wael Abdallah

Risks 2022, 10(3), 53; https://doi.org/10.3390/risks10030053 - 01 Mar 2022

Cited by 4 | Viewed by 3197

Abstract

This paper aimed to assess the effect of the cryptocurrency market on firms’ market value, especially on the sectoral level, in Africa. To reach the study’s main goal, the authors adopted the Panel-Corrected Standard Errors (PCSEs) and Panel Double-Clustered Standard Errors (PDCSEs). Using [...] Read more.

This paper aimed to assess the effect of the cryptocurrency market on firms’ market value, especially on the sectoral level, in Africa. To reach the study’s main goal, the authors adopted the Panel-Corrected Standard Errors (PCSEs) and Panel Double-Clustered Standard Errors (PDCSEs). Using firm-level data, the results of this study can be summarized as follows: (a) The cryptocurrency market hurts the firm market value in Africa. (b) The firms operating across different sectors respond disproportionally to the cryptocurrency market. For instance, the sectors that offer low returns in Africa (industrial, energy, financial) negatively respond to the cryptocurrency market, while the sectors that offer high returns (real estate and information technology) are not significantly affected. (c) The cryptocurrency market has a perverse effect on less experienced and highly indebted firms. (d) The consistent policies of governments to ban cryptocurrency do not work efficiently. Full article

(This article belongs to the Special Issue Cryptocurrencies and Risk Management)

Open AccessArticle

A Critical Analysis of Volatility Surprise in Bitcoin Cryptocurrency and Other Financial Assets

by

Yianni Doumenis

,

Javad Izadi

,

Pradeep Dhamdhere

,

Epameinondas Katsikas

and

Dimitrios Koufopoulos

Risks 2021, 9(11), 207; https://doi.org/10.3390/risks9110207 - 12 Nov 2021

Cited by 7 | Viewed by 5782

Abstract

The purpose of this paper is to investigate the viability as compared with other financial assets of cryptocurrencies as a currency or as an asset investment. This paper also aims to see which macro variable relates more to the price of cryptocurrencies, especially [...] Read more.

The purpose of this paper is to investigate the viability as compared with other financial assets of cryptocurrencies as a currency or as an asset investment. This paper also aims to see which macro variable relates more to the price of cryptocurrencies, especially Bitcoin. Since the whole concept of cryptocurrencies is quite novel, an attempt has been made to briefly explain the underlying blockchain technology that forms the bedrock of cryptocurrencies. In this study, we use secondary data, i.e., the price history of Bitcoin from September 2014 to September 2021 for the last seven years, captured from trading exchanges. We predicted monthly returns of Bitcoin with that of Standard & Poor’s 500 Index (S&P 500), gold, and Treasury Bonds. Our findings show that Bitcoin has very high volatility compared to S&P 500, Gold and Treasury Bonds. Also, our findings show that there is a positive correlation between Bitcoin’s price volatility and the other three financial assets before and during COVID-19. Hence, Bitcoin is acting more as a speculative asset rather than a steady store of value. This can be drawn from the comparison with the debt market i.e., a Treasury Bond that invests in long-dated (30 years) US treasuries with which Bitcoin shows no relationship. The findings of this study could help with understanding the future of Bitcoin. This has important implications for Bitcoin investors. The current study contributes to the extant literature by providing empirical evidence on long-term social sustainability vis-à-vis supply chain traceability. Full article

(This article belongs to the Special Issue Cryptocurrencies and Risk Management)

► Show Figures

Figure 1

Open AccessArticle

Bitcoin as an Investment and Hedge Alternative. A DCC MGARCH Model Analysis

by

Karl Oton Rudolf

,

Samer Ajour El Zein

and

Nicola Jackman Lansdowne

Risks 2021, 9(9), 154; https://doi.org/10.3390/risks9090154 - 26 Aug 2021

Cited by 8 | Viewed by 7419

Abstract

Volatility and investor sentiment have been factors for the slow adoption rate of Bitcoin (BTC) that was first recognized in 2008 as a potential store of value, investment vehicle and a hedge alternative to gold during a recession. The purpose of this applied [...] Read more.

Volatility and investor sentiment have been factors for the slow adoption rate of Bitcoin (BTC) that was first recognized in 2008 as a potential store of value, investment vehicle and a hedge alternative to gold during a recession. The purpose of this applied mathematics study will use a multivariate DCC GARCH model. Bitcoin holds its ground in volatility. This study examines Bitcoin as an investment and hedge alternative to gold as well as the major stock index. To perform the research to explore the viability of Bitcoin as an investment and hedge alternative to gold, the authors conducted a DCC GARCH model analysis. The findings of this research paper confirm Bitcoin’s cyclical performance between volatility and adoption. The findings give a strong ground for Bitcoin as the new digital currency, store of value, medium of exchange, and a unit of account and incentivize further research by theorists, scholars and examiners. The significance of this applied mathematics research and analysis will allow an unstoppable, incorruptible, and uncontrollable store of value, and investment vehicle, without governmental or institutional intervention. This study contributes by comparing and contrasting volatility stability based on the return levels of each Bitcoin on major indexes traded with BTC (based on fiat currencies) and gold. Full article

(This article belongs to the Special Issue Cryptocurrencies and Risk Management)

► Show Figures

Figure 1

Review

Jump to: Research, Other

Open AccessReview

Economic Policy Uncertainty and Cryptocurrency Market as a Risk Management Avenue: A Systematic Review

by

,

,

,

and

Risks 2021, 9(9), 163; https://doi.org/10.3390/risks9090163 - 07 Sep 2021

Cited by 26 | Viewed by 7988

Abstract

Cryptocurrency literature is increasing rapidly nowadays. Particularly, the role of the cryptocurrency market as a risk management avenue has got the attention of researchers. However, it is an immature asset class and requires gaps in current literature for future research directions. This research [...] Read more.

Cryptocurrency literature is increasing rapidly nowadays. Particularly, the role of the cryptocurrency market as a risk management avenue has got the attention of researchers. However, it is an immature asset class and requires gaps in current literature for future research directions. This research provides a systematic review of the vast range empirical literature based on the cryptocurrency market as a risk management avenue against economic policy uncertainty (EPU). The review discovers that cryptocurrencies have mixed connectedness patterns with all national EPU therefore, the risk mitigation ability varies from country to country. The review finds that heterogeneous correlation patterns are due to the dependence of EPU on the policies and decisions usually taken by regulatory authorities of a particular country. Additionally, heterogeneous EPU requires heterogeneous solutions to deal with stock market volatility and economic policy uncertainty in different economies. Likewise, the divergent protocol and administration of currencies in the crypto market consequently vicissitudes the hedging and diversification performance against each economy. Many research lines can benefit investors, policymakers, fund managers, or portfolio managers. Therefore, the authors suggested future research avenues in terms of topics, data frequency, and methodologies. Full article

(This article belongs to the Special Issue Cryptocurrencies and Risk Management)

► Show Figures

Figure 1

Other

Jump to: Research, Review

Open AccessTechnical Note

Flared Gas Can Reduce Some Risks in Crypto Mining as Well as Oil and Gas Operations

by

Jennifer Vazquez

and

Donald Larry Crumbley

Risks 2022, 10(6), 127; https://doi.org/10.3390/risks10060127 - 16 Jun 2022

Cited by 3 | Viewed by 4034

Abstract

There are numerous risks associated with mining and owning cryptocurrencies, and exploring and producing oil and natural gas are highly risky, costly, and controversial. A marriage of digital mining and exploring and producing oil and natural gas has reduced the major risks and [...] Read more.

There are numerous risks associated with mining and owning cryptocurrencies, and exploring and producing oil and natural gas are highly risky, costly, and controversial. A marriage of digital mining and exploring and producing oil and natural gas has reduced the major risks and costs for both the crypto miner and the petroleum industry. On the one hand, crypto mining requires an enormous amount of electricity, which is not environmentally friendly. On the other hand, when drilling for petroleum resources, natural gas is often discovered, but due to a lack of resources or pipeline availability, a massive amount of natural gas is vented into the atmosphere or burned (called flaring). Today, however, this normally wasted gas (called stranded natural gas) is being used to create cheap electricity for mining server containers stationed near drilling rigs, which are used to create cryptocurrencies. This results in reduced CO₂ emissions, lower costs for drillers, and greater royalties going to landowners. Full article

(This article belongs to the Special Issue Cryptocurrencies and Risk Management)

► Show Figures

Figure 1

Journal Menu

Journal Browser

Special Issue "Cryptocurrencies and Risk Management"

Share This Special Issue

Special Issue Editor

Special Issue Information

Published Papers (10 papers)

Research

Review

Other

Further Information

Guidelines

MDPI Initiatives

Follow MDPI