18 Hits in 1.6 sec

Forecasting Bitcoin Price with Graph Chainlets [chapter]

Cuneyt G. Akcora, Asim Kumer Dey, Yulia R. Gel, Murat Kantarcioglu
2018 Lecture Notes in Computer Science  
Furthermore, we assess the role of chainlets on Bitcoin price formation and dynamics.  ...  We introduce a novel concept of chainlets, or Bitcoin subgraphs, which allows us to evaluate the local topological structure of the Bitcoin graph over time.  ...  For 1-step ahead forecast, chainlets and other covariates do not contribute useful predictive information over history of Bitcoin price.  ... 
doi:10.1007/978-3-319-93040-4_60 fatcat:32wvgkystzgkthrickfepqta4i

Bitcoin Risk Modeling with Blockchain Graphs [article]

Cuneyt Akcora, Matthew Dixon, Yulia Gel, Murat Kantarcioglu
2018 arXiv   pre-print
In particular, we identify certain sub-graphs ('chainlets') that exhibit predictive influence on Bitcoin price and volatility, and characterize the types of chainlets that signify extreme losses.  ...  By processing all transactions, we model the network with a high fidelity graph so that it is possible to characterize how the flow of information in the network evolves over time.  ...  strongly linked with Bitcoin price changes [9, 10] .  ... 
arXiv:1805.04698v1 fatcat:5qo2k5suzjcinl7jel6onysthu

Blockchain analytics for intraday financial risk modeling

Matthew F. Dixon, Cuneyt Gurcan Akcora, Yulia R. Gel, Murat Kantarcioglu
2019 Digital Finance  
Specifically, we identify certain sub-graphs ('chainlets') that exhibit predictive influence on Bitcoin price and volatility and characterize the types of chainlets that signify extreme losses.  ...  In this article, we demonstrate the impact of extreme transaction graph activity on the intraday volatility of the Bitcoin prices series.  ...  Extreme chainlets Graph analysis allows us to evaluate the local topological structure of the Bitcoin graph over time and assess the role of chainlets on Bitcoin price formation and dynamics.  ... 
doi:10.1007/s42521-019-00009-8 fatcat:7bmjaqu6grco7cj4z7fxvusgey

ChainNet: Learning on Blockchain Graphs with Topological Features [article]

Nazmiye Ceren Abay, Cuneyt Gurcan Akcora, Yulia R. Gel, Umar D. Islambekov, Murat Kantarcioglu, Yahui Tian, Bhavani Thuraisingham
2019 arXiv   pre-print
With emergence of blockchain technologies and the associated cryptocurrencies, such as Bitcoin, understanding network dynamics behind Blockchain graphs has become a rapidly evolving research direction.  ...  We show that standard graph features such as degree distribution of the transaction graph may not be sufficient to capture network dynamics and its potential impact on fluctuations of Bitcoin price.  ...  graph features in machine learning models such as random forest for assessment of their utility in price forecasting.  ... 
arXiv:1908.06971v1 fatcat:nh5cmdqrobajfjpjxyno7b2er4

Using Networks and Partial Differential Equations to Predict Bitcoin Price [article]

Yufang Wang, Haiyan Wang
2020 arXiv   pre-print
Through analysis of bitcoin subgraphs or chainlets, the PDE model captures the influence of transaction patterns on bitcoin price over time and combines the effect of all chainlet clusters.  ...  The results demonstrate the PDE model is capable of predicting bitcoin price. The paper is the first attempt to apply a PDE model to the bitcoin transaction network for predicting bitcoin price.  ...  They combined "chainlets" of the Bitcoin transaction networks with statistical models to predict bitcoin price.  ... 
arXiv:2001.03099v1 fatcat:gxzl5mcwybgzxjvdsavlv6zwfa

Machine Learning in/for Blockchain: Future and Challenges [article]

Fang Chen, Hong Wan, Hua Cai, Guang Cheng
2020 arXiv   pre-print
of coins transferred Figure 2 : 2 A Transaction-Address Graph by chainlets.  ...  A price prediction model is further developed using significant chainlets.  ... 
arXiv:1909.06189v3 fatcat:4wxvpsli5bcoldwseem2jpxnue

A Blockchain Transaction Graph based Machine Learning Method for Bitcoin Price Prediction [article]

Xiao Li, Weili Wu
2020 arXiv   pre-print
Bitcoin price prediction task is consequently a rising academic topic for providing valuable insights and suggestions.  ...  In this paper, we aim to mining the abundant patterns encoded in bitcoin transactions, and propose k-order transaction graph to reveal patterns under different scope.  ...  Akcora et. al [9] propose a bitcoin graph model, upon which Chainlets is proposed to represent graph structures in the Bitcoin.  ... 
arXiv:2008.09667v1 fatcat:5xejpzppfvebtmltgf4uzlso2u

Adaptive Deep Learning based Cryptocurrency Price Fluctuation Classification

Ahmed Saied El-Berawi, Mohamed Abdel Fattah Belal, Mahmoud Mahmoud Abd Ellatif
2021 International Journal of Advanced Computer Science and Applications  
., price is not totally a random walk phenomenon. Based upon this, this study proves that the price value forecast and price movement direction classification is both predictable.  ...  This paper proposes a deep learning based predictive model for forecasting and classifying the price of cryptocurrency and the direction of its movement.  ...  Chainlets allow researchers to examine the influence of the blockchain's local topological structure on Bitcoin and Litecoin price development and evolution.  ... 
doi:10.14569/ijacsa.2021.0121264 fatcat:rpjmpftytvhubouu3odadgumqq

Predictions of bitcoin prices through machine learning based frameworks

Luisanna Cocco, Roberto Tonelli, Michele Marchesi
2021 PeerJ Computer Science  
The main goal of this work is to compare several frameworks each other to predict the daily closing Bitcoin price, investigating those that provide the best performance, after a rigorous model selection  ...  in agreement with those reported in recent literature works.  ...  Akcora et al. (2018) introduced the concept of k-chainlets expanding the concepts of motifs and graphlets to Blockchain graphs.  ... 
doi:10.7717/peerj-cs.413 pmid:33834099 pmcid:PMC8022579 fatcat:f27wmrbqyfc6jfcfcnbqbug4ii

Kripto Para Fiyatlarının Tahmininde Gri Sistem Teorisi: Yöntemsel Karşılaştırma

Eyyüp Ensari ŞAHİN, Buğra BAĞCI
2020 Anadolu Üniversitesi Sosyal Bilimler Dergisi  
The aim of this study is to predict the future price of cryptocurrencies with different infrastructural features such as Bitcoin, Ethereum, IOTA and Ripple, based on the prices of the past.  ...  In the study, price estimation was made with the grey system theory introduced by Deng Ju-Long in the 1980s. The past prices used in the study cover the 11day process.  ...  Forecasting Bitcoin price with graph chainlets. Proceedings of the Pacific-Asia Conference on Knowledge Discovery and Data Mining, Springer, Cham, 765-776.  ... 
doi:10.18037/ausbd.700349 fatcat:nrocech6wnfg3nwnayso5yfasi

Is It Possible to Forecast the Price of Bitcoin?

Julien Chevallier, Dominique Guégan, Stéphane Goutte
2021 Forecasting  
This paper focuses on forecasting the price of Bitcoin, motivated by its market growth and the recent interest of market participants and academics.  ...  Forecasting results point to the segmentation of Bitcoin concerning alternative assets. Finally, trading strategies are implemented.  ...  -sample with the Introduction of Tether (USDT): Forecasting of the CME Bitcoin Fu- tures price.  ... 
doi:10.3390/forecast3020024 fatcat:5nocd7gm3zhrpfbgi3tgejjqdm

A Survey on Volatility Fluctuations in the Decentralized Cryptocurrency Financial Assets

Nikolaos A. Kyriazis
2021 Journal of Risk and Financial Management  
Overall, it is found that the inclusion of Bitcoin in portfolios with conventional assets could significantly improve the risk–return trade-off of investors' decisions.  ...  Results on whether Bitcoin resembles gold are split. The same is true about whether Bitcoins volatility presents larger reactions to positive or negative shocks.  ...  To be more precise, Akcora et al. (2018) employ blockchain graphs and subgraphs (chainlets) as well as GARCH modeling to predict influences on Bitcoin price and volatility.  ... 
doi:10.3390/jrfm14070293 fatcat:zgfkjue2cbc5xhnafufrudfl7i

A Survey of State-of-the-Art on Blockchains: Theories, Modelings, and Tools [article]

Huawei Huang, Wei Kong, Sicong Zhou, Zibin Zheng, Song Guo
2020 arXiv   pre-print
Predicting volatility of Bitcoin price [111] Various graph characteristics of extreme chainlets Authors proposed a graph-based analytic model to predict the intraday financial risk of Bitcoin market.  ...  Through the analysis of chainlet activities [112] in the constructed graph, they proposed to use GARCH-based forecasting models to identify the financial risk of Bitcoin market for cryptocurrency users  ... 
arXiv:2007.03520v2 fatcat:3lvd5dhkajdhbcwlh6vtdl7nlq

Dissecting Ethereum Blockchain Analytics: What We Learn from Topology and Geometry of Ethereum Graph [article]

Yitao Li and Umar Islambekov and Cuneyt Akcora and Ekaterina Smirnova and Yulia R. Gel and Murat Kantarcioglu
2019 arXiv   pre-print
As a result, this allows us to construct a transaction graph and to assess not only its organization but to glean relationships between transaction graph properties and crypto price dynamics.  ...  strikes of crypto-tokens that are otherwise largely inaccessible with conventional data sources and traditional analytic methods.  ...  Recently, [2] employed blockchain motifs, termed chainlets, as features to predict Bitcoin price. However, all the mentioned approaches are carried out to track a single cryptocurrency.  ... 
arXiv:1912.10105v1 fatcat:zcde4yu4wfdqtdb5mts55f57fq

Analysis of Cryptocurrency Transactions from a Network Perspective: An Overview [article]

Jiajing Wu, Jieli Liu, Yijing Zhao, Zibin Zheng
2021 arXiv   pre-print
These transaction records containing rich information and complete traces of financial activities are publicly accessible, thus providing researchers with unprecedented opportunities for data mining and  ...  In Akcora et al. (2018b) , chainlet motifs are employed to conduct price prediction and risk modeling of Bitcoin.  ...  And in 2017, the price of bitcoins even came up to a peak point of approximately $20,000 per bitcoin.  ... 
arXiv:2011.09318v2 fatcat:idtd636e75cotgfsgufgu6np3a
« Previous Showing results 1 — 15 out of 18 results