Predicting Bitcoin Volatility Using Machine Learning Algorithms and Blockchain Technology
Date Issued
2022
Author(s)
Mijoska, Mimoza
Ristevski, Blagoj
Savoska, Snezana
Trajkovik, Vladimir
Abstract
Blockchain technology has the potential to be applied in a variety of areas
of our daily life. Blockchain is the foundation of cryptocurrency, but the
applications of blockchain technology are much more expansive. This
technology is considered to be a revolutionary solution for the financial
industry. Also, it can be successfully applied in scenarios involving data
validation, auditing, and sharing. On the other hand, machine learning is
one of the most noticeable technologies in recent years. Both technologies
are data-driven, and thus there are rapidly growing interests in integrating
them for more secure and efficient data sharing and analysis. This paper
shows how these two technologies, blockchain and machine learning,
can be combined in predicting bitcoin volatility. To analyze and predict
bitcoin volatility, bitcoin data from real-time series and random forests as a
machine learning algorithm were used. When predicting bitcoin volatility,
low statistical errors were obtained in the training and test set. This confirms
that the forecasting model is well designed.
of our daily life. Blockchain is the foundation of cryptocurrency, but the
applications of blockchain technology are much more expansive. This
technology is considered to be a revolutionary solution for the financial
industry. Also, it can be successfully applied in scenarios involving data
validation, auditing, and sharing. On the other hand, machine learning is
one of the most noticeable technologies in recent years. Both technologies
are data-driven, and thus there are rapidly growing interests in integrating
them for more secure and efficient data sharing and analysis. This paper
shows how these two technologies, blockchain and machine learning,
can be combined in predicting bitcoin volatility. To analyze and predict
bitcoin volatility, bitcoin data from real-time series and random forests as a
machine learning algorithm were used. When predicting bitcoin volatility,
low statistical errors were obtained in the training and test set. This confirms
that the forecasting model is well designed.
Subjects
File(s)![Thumbnail Image]()
Loading...
Name
paper30.pdf
Size
549.86 KB
Format
Adobe PDF
Checksum
(MD5):48c6d2baab68389a4dfa7e516ad08010