Towards Characterizing Blockchain-Based Cryptocurrencies For Highly-Accurate Predictions
Keywords
Bitcoin; Blockchain; modeling; prediction
Abstract
In 2017, the Blockchain-based crypto currency market witnessed enormous growth. Bitcoin, the leading crypto currency, reached all-time highs many times over the year leading to speculations to explain the trend in its growth. In this paper, we study Bitcoin and explore features in its network that explain its price hikes. We gather data and analyze user and network activity that highly impact Bitcoin price. We monitor the change in the activities over time and relate them to economic theories. We identify key network features that determine the demand and supply dynamics of a crypto currency. Finally, we use machine learning methods to construct models that predict Bitcoin price. Our regression model predicts Bitcoin price with 99.4% accuracy and 0.0113 root mean squared error (RMSE).
Publication Date
7-6-2018
Publication Title
INFOCOM 2018 - IEEE Conference on Computer Communications Workshops
Number of Pages
704-709
Document Type
Article; Proceedings Paper
Personal Identifier
scopus
DOI Link
https://doi.org/10.1109/INFCOMW.2018.8406859
Copyright Status
Unknown
Socpus ID
85050684069 (Scopus)
Source API URL
https://api.elsevier.com/content/abstract/scopus_id/85050684069
STARS Citation
Saad, Muhammad and Mohaisen, Aziz, "Towards Characterizing Blockchain-Based Cryptocurrencies For Highly-Accurate Predictions" (2018). Scopus Export 2015-2019. 10534.
https://stars.library.ucf.edu/scopus2015/10534