Crypto Currency Price Forecast: Neural Network Perspectives

The study examines the problem of modeling and forecasting the price dynamics of crypto currencies. We use machine learning techniques to forecast the price of crypto currencies. The FB Prophet time series model and the LSTM recurrent neural network were selected to implement the study. Using the ex...

Full description

Saved in:
Bibliographic Details
Main Authors: Yuriy Kleban, Tetiana Stasiuk
Format: Article
Language:English
Published: National Bank of Ukraine 2022-12-01
Series:Visnyk of the National Bank of Ukraine
Subjects:
Online Access:https://journal.bank.gov.ua/en/article/2022/254/03
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1832584852209139712
author Yuriy Kleban
Tetiana Stasiuk
author_facet Yuriy Kleban
Tetiana Stasiuk
author_sort Yuriy Kleban
collection DOAJ
description The study examines the problem of modeling and forecasting the price dynamics of crypto currencies. We use machine learning techniques to forecast the price of crypto currencies. The FB Prophet time series model and the LSTM recurrent neural network were selected to implement the study. Using the example of data from Binance (the most popular exchange in Ukraine) for the period from 06.07.2020 to 01.04.2023, prices for Bitcoin, Ethereum, Ripple, and Dogecoin were modeled and forecasted. The recurrent neural network of long-term memory showed significantly better results in forecasting according to the RMSE, MAE, and MAPE criteria, compared to the Naïve model, the traditional ARIMA model, and the FB Prophet results.
format Article
id doaj-art-3c043d8d3b0f495f907d58114fee59be
institution Kabale University
issn 2414-987X
language English
publishDate 2022-12-01
publisher National Bank of Ukraine
record_format Article
series Visnyk of the National Bank of Ukraine
spelling doaj-art-3c043d8d3b0f495f907d58114fee59be2025-01-27T10:27:21ZengNational Bank of UkraineVisnyk of the National Bank of Ukraine2414-987X2022-12-01254294210.26531/vnbu2022.254.03Crypto Currency Price Forecast: Neural Network PerspectivesYuriy Kleban0https://orcid.org/0000-0002-7070-5175Tetiana Stasiuk1https://orcid.org/0009-0008-5606-2557National University of Ostroh AcademyNational University of Ostroh AcademyThe study examines the problem of modeling and forecasting the price dynamics of crypto currencies. We use machine learning techniques to forecast the price of crypto currencies. The FB Prophet time series model and the LSTM recurrent neural network were selected to implement the study. Using the example of data from Binance (the most popular exchange in Ukraine) for the period from 06.07.2020 to 01.04.2023, prices for Bitcoin, Ethereum, Ripple, and Dogecoin were modeled and forecasted. The recurrent neural network of long-term memory showed significantly better results in forecasting according to the RMSE, MAE, and MAPE criteria, compared to the Naïve model, the traditional ARIMA model, and the FB Prophet results.https://journal.bank.gov.ua/en/article/2022/254/03forecastingneural networkscrypto currencytime series
spellingShingle Yuriy Kleban
Tetiana Stasiuk
Crypto Currency Price Forecast: Neural Network Perspectives
Visnyk of the National Bank of Ukraine
forecasting
neural networks
crypto currency
time series
title Crypto Currency Price Forecast: Neural Network Perspectives
title_full Crypto Currency Price Forecast: Neural Network Perspectives
title_fullStr Crypto Currency Price Forecast: Neural Network Perspectives
title_full_unstemmed Crypto Currency Price Forecast: Neural Network Perspectives
title_short Crypto Currency Price Forecast: Neural Network Perspectives
title_sort crypto currency price forecast neural network perspectives
topic forecasting
neural networks
crypto currency
time series
url https://journal.bank.gov.ua/en/article/2022/254/03
work_keys_str_mv AT yuriykleban cryptocurrencypriceforecastneuralnetworkperspectives
AT tetianastasiuk cryptocurrencypriceforecastneuralnetworkperspectives