Predicting Fluctuations in Cryptocurrency Transactions Based on User Comments and Replies

Kim, Young Bin; Kim, Jun Gi; Kim, Wook; Im, Jae Ho; Kim, Tae Hyeong; Kang, Seong-Hoon; Kim, Chang Hun

doi:10.1371/journal.pone.0161197

Cited by 226 publications

(150 citation statements)

References 30 publications

Supporting

Mentioning

144

Contrasting

Unclassified

Order By: Relevance

“…The high volatility of Bitcoin is well-documented (Blundell-Wignall 2014, Lo 2014. Some econometric methods have been applied to predict Bitcoin volatility estimates such as (Katsiampa 2017, Kim 2016, Kristoufek 2015.…”

Section: Introductionmentioning

confidence: 99%

A Gated Recurrent Unit Approach to Bitcoin Price Prediction

Dutta

Kumar

Basu

2020

JRFM

146

View full text Add to dashboard Cite

In today's era of big data, deep learning and artificial intelligence have formed the backbone for cryptocurrency portfolio optimization. Researchers have investigated various state of the art machine learning models to predict Bitcoin price and volatility. Machine learning models like recurrent neural network (RNN) and long short-term memory (LSTM) have been shown to perform better than traditional time series models in cryptocurrency price prediction. However, very few studies have applied sequence models with robust feature engineering to predict future pricing. In this study, we investigate a framework with a set of advanced machine learning forecasting methods with a fixed set of exogenous and endogenous factors to predict daily Bitcoin prices. We study and compare different approaches using the root mean squared error (RMSE). Experimental results show that gated recurring unit (GRU) model with recurrent dropout performs better than popular existing models. We also show that simple trading strategies, when implemented with our proposed GRU model and with proper learning, can lead to financial gain.

show abstract

Section: Introductionmentioning

confidence: 99%

A Gated Recurrent Unit Approach to Bitcoin Price Prediction

Dutta

Kumar

Basu

2020

JRFM

146

View full text Add to dashboard Cite

show abstract

“…We also plan to study the effect of market-making information using open access texts (cf. Kim et al, 2016). The present findings may also be useful in considerations of the design of future cryptocurrencies other than Bitcoin (Extance, 2015).…”

Section: Resultsmentioning

confidence: 73%

“…The present findings may also be useful in considerations of the design of future cryptocurrencies other than Bitcoin (Extance, 2015). The presented work is also relevant and interesting due to the limited number of available data analysis papers on the Bitcoin subject, although the situation has improved recently (Houey, 2016;Kim et al, 2016, Kristoufek, 2013Lahmiri, 2011;Ron and Shamir, 2013) as new cryptocurrency journals are introduced and technical reports of central banks all over the world start to pay attention to this still relatively young phenomenon.…”

Section: Resultsmentioning

confidence: 99%

Regime Change and Trend Prediction for Bitcoin Time Series Data

Kodama

Pichl

Kaizoji

2017

CBUP

View full text Add to dashboard Cite

Bitcoin time series dataset recording individual transactions denominated in Euro at the COINBASE market between April 23, 2015 and August 15, 2016 is analyzed. Markov switching model is applied to classify the regions of varying volatility represented by three hidden state regimes using univariate autoregressive model and dependent mixture model. Causality extraction and price prediction of daily BTCEUR exchange rates is performed by means of a recurrent neural network using the standard Elman model. Strong correlations is found between the normalized mean squared error of the Elman network (out-of-sample 5-day-ahead prediction) and the realized volatility (sum of minute returns squared throughout the trading day). The present approach is calibrated using simulated regime change in standard econometric models. Our results clearly demonstrate the applicability of recurrent neural networks to causality extraction even in the case of highly volatile cryptocurrency exchange rate time series data. IntroductionBitcoin is a cryptocurrency released as an open-source software in 2009, which represents a transaction payment system as well as a sort of digital commodity (Bohme et al., 2016). The bitcoin market capitalization as of early 2017 has reached USD 20 billion (CoinDesk, 2017). Free of any interventions from regulatory authorities, such as central banks, the distributed block chain system on which Bitcoin is based meets varying levels of demand for transaction settlement, and the Bitcoin exchange rate series to major currencies such as USD, EUR or GBP are known to highly fluctuate -it is not uncommon that gains or losses in tens of percent occur within a week, if not during a single day. There exist various Bitcoin exchange markets, such as BitBay, Btcde, Kraken, LocalBtc, or Rock for EUR currency, to name just a few of the currently active BTCEUR exchanges. The highly volatile nature of the exchange rate represents an ideal environment for the study of the extreme events in the field of financial time series. Prediction of extreme events is a key issue not only in economics, but also in climatology, geosciences, civil engineering, space technology, etc. In spite of its importance, the topic is rather under-studied, in our opinion. In this work, we explore the applicability of computational intelligence methods from financial analysis to the series of Bitcoin exchange rates (data shown in Fig. 1). Since the Bitcoin price process is not stationary but exhibits an appreciation trend, we transform the time series data to the logarithmic returns. If the absolute value of the log return is large, it corresponds to an extreme event (bullish or bearish, based on the sign). Next we adopt the Hidden Markov Model to categorize the market regime into 3 modes: stable, intermediate, and volatile. This approach is excellent in ex-post analysis of the data, however lacks in the predictive power for future trend prediction. Consequently, we add the realized volatility as an intraday indicator of market stability, and d...

show abstract

“…We gathered data from official WoW forums. People use these Internet forums to upload postings and exchange opinions regarding particular topics of common interest [1,[31][32][33][34][35]. Therefore, such online forums are good sources of information to gauge the daily reactions of many users to certain MMOGs.…”

Section: Data Crawlingmentioning

confidence: 99%

Predicting the Currency Market in Online Gaming via Lexicon-Based Analysis on Its Online Forum

Kim¹,

Kang²,

Choo³

et al. 2017

Complexity

Self Cite

View full text Add to dashboard Cite

Transactions involving virtual currencies are becoming increasingly common, including those in online games. In response, predicting the market price of a virtual currency is an important task for all involved, but it has not yet attracted much attention from researchers. This paper presents user opinions from online forums in a massive multiplayer online game (MMOG) setting widely used around the world. We propose a method for predicting the next-day rise and fall of the currency used in an MMOG environment. Based on analysis of online forum users' opinions, we predict daily fluctuations in the price of a currency used in an MMOG setting. Focusing specifically on the World of Warcraft game, one of the most widely used MMOGs, we demonstrate the feasibility of predicting the fluctuation in value of virtual currencies used in this game community.

show abstract

Predicting Fluctuations in Cryptocurrency Transactions Based on User Comments and Replies

Cited by 226 publications

References 30 publications

A Gated Recurrent Unit Approach to Bitcoin Price Prediction

A Gated Recurrent Unit Approach to Bitcoin Price Prediction

Regime Change and Trend Prediction for Bitcoin Time Series Data

Predicting the Currency Market in Online Gaming via Lexicon-Based Analysis on Its Online Forum

Contact Info

Product

Resources

About