Bitcoin price prediction using ensembles of neural networks

Sin, Edwin; Wang, Lipo

doi:10.1109/fskd.2017.8393351

Cited by 101 publications

(43 citation statements)

References 38 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Our experiments show that: 1) C2P2 beats [2]'s method on all 21 cryptocurrencies by a margin of 5.1-83% (depending on which of the four prediction types is considered) which is substantial and is statistically significant when comparing model performances across all 21 cryptocurrencies (p < 10 −5 ). 2) C2P2 beats [3] on Bitcoin data by 16% for Close-Close task, which is also statistically significant (p < 10 −5 ).…”

Section: Introductionmentioning

confidence: 68%

“…In this experiment, we compare C2P2 with [2] for all 21 cryptocurrencies and compare with [3] for Bitcoin (as only Bitcoin-related features were used in [3]).…”

Section: Experiments 1: Comparison Of C2p2 and Baselinesmentioning

confidence: 99%

“…Bitcoin price prediction is the topic of most papers in the area of cryptocurrency price prediction. References [2], [3], [7], [8] leveraged blockchain features to predict Bitcoin price with varying degrees of success. Sin et al [3] achieved 64% classification accuracy in predicting the sign of price change using an ensemble of neural networks tuned with genetic algorithms.…”

Section: Related Workmentioning

confidence: 99%

“…References [2], [3], [7], [8] leveraged blockchain features to predict Bitcoin price with varying degrees of success. Sin et al [3] achieved 64% classification accuracy in predicting the sign of price change using an ensemble of neural networks tuned with genetic algorithms. Jang et al [7] produced a regression with a Mean Average Percent Error (MAPE) of 0.0138 using Bayesian Neural Networks.…”

Section: Related Workmentioning

confidence: 99%

See 3 more Smart Citations

C2P2: A Collective Cryptocurrency Up/Down Price Prediction Engine

Bai

White

Xiao

et al. 2019

2019 IEEE International Conference on Blockchain (Blockchain)

View full text Add to dashboard Cite

We study the problem of predicting whether the price of the 21 most popular cryptocurrencies (according to coinmarketcap.com) will go up or down on day d, using data up to day d−1. Our C2P2 algorithm is the first algorithm to consider the fact that the price of a cryptocurrency c might depend not only on historical prices, sentiments, global stock indices, but also on the prices and predicted prices of other cryptocurrencies. C2P2 therefore does not predict cryptocurrency prices one coin at a time -rather it uses similarity metrics in conjunction with collective classification to compare multiple cryptocurrency features to jointly predict the cryptocurrency prices for all 21 coins considered. We show that our C2P2 algorithm beats out a recent competing 2017 paper by margins varying from 5.1-83% and another Bitcoin-specific prediction paper from 2018 by 16%. In both cases, C2P2 is the winner on all cryptocurrencies considered. Moreover, we experimentally show that the use of similarity metrics within our C2P2 algorithm leads to a direct improvement for 20 out of 21 cryptocurrencies ranging from 0.4% to 17.8%. Without the similarity component, C2P2 still beats competitors on 20 out of 21 cryptocurrencies considered. We show that all these results are statistically significant via a Student's t-test with p < 10 −5 .

show abstract

Section: Introductionmentioning

confidence: 68%

“…In this experiment, we compare C2P2 with [2] for all 21 cryptocurrencies and compare with [3] for Bitcoin (as only Bitcoin-related features were used in [3]).…”

Section: Experiments 1: Comparison Of C2p2 and Baselinesmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

See 2 more Smart Citations

C2P2: A Collective Cryptocurrency Up/Down Price Prediction Engine

Bai

White

Xiao

et al. 2019

2019 IEEE International Conference on Blockchain (Blockchain)

View full text Add to dashboard Cite

show abstract

“…Huisu Jang et al [18] they concern about study on modelling and prediction bitcoin with Bayesian Neural Network and giving some knowledge about bitcoin. Edwin sin et al [19] provide topic Bitcoin price predictiom using Ensemble of Neural. Networks.…”

Section: Overview Of Economic Value Estimation Cryptocurrency In Compmentioning

confidence: 99%

A Study of Economic Value Estimation on Cryptocurrency Value back by Gold, Methods, Techniques, and Tools

et al. 2019

View full text Add to dashboard Cite

After Bitcoin Introduced around the world, many Cryptocurrencies was created that followed the standard of bitcoin. The use of Bitcoin or other Cryptocurrency as a currency is also an interesting study from an Islamic economic perspective. They tried to use gold with value back by gold , which gold itself is famous for its exchange rate stability.From abu bakar There is a need for monitoring organization of the cryptocurrency, to controlling from Riba (Interest), Maysir (gambling) and ghahar (Uncertainty). To solve this problem there is a need a tool that can predict with certainty based on valid historical data, to produce accurate prediction results and produce Economic value estimations that are close to Gold real value. With the results we can monitoring day by day, see next day value and continuously based on Cryptocurrency with value back by gold, and see what other impact influences the value by looking the factor negative or positive with sentiment analysis. In the last section we discuss and provide method that we analyse from previous work to produce method to estimate value cryptocurrency value back by gold.Ferdiansyah 1 , Siti Hajar Othman 2 , at all | 179 the first cryptocurrency has enjoyed huge success with the capital market reaching 10 billion dollars in 2016 [1].

show abstract

Forecasting and trading Bitcoin with machine learning techniques and a hybrid volatility/sentiment leverage

Wei

Sermpinis

Stasinakis

2022

Journal of Forecasting

View full text Add to dashboard Cite

This paper explores the use of machine learning algorithms and narrative sentiments when applied to the task of forecasting and trading Bitcoin. The forecasting framework starts from the selection among 295 individual prediction models. Three machine learning approaches, namely, neural networks, support vector machines, and gradient boosting approach, are used to further improve the forecasting performance of individual models. By taking datasnooping bias into account, three different metrics are applied to examine the forecasting ability of each model. Our results suggest that the machine learning techniques always outperform the best individual model whereas the gradient boosting framework has the best performance among all the models. Finally, a time-varying leverage trading strategy combined with narrative sentiments and volatility is proposed to enhance trading performance. This suggests that the hybrid leverage strategy provides the highest Bitcoin profits consistently among all trading exercises.

show abstract

Bitcoin price prediction using ensembles of neural networks

Cited by 101 publications

References 38 publications

C2P2: A Collective Cryptocurrency Up/Down Price Prediction Engine

C2P2: A Collective Cryptocurrency Up/Down Price Prediction Engine

A Study of Economic Value Estimation on Cryptocurrency Value back by Gold, Methods, Techniques, and Tools

Forecasting and trading Bitcoin with machine learning techniques and a hybrid volatility/sentiment leverage

Contact Info

Product

Resources

About