Assessing machine learning performance in cryptocurrency market price prediction
Cryptocurrencies, which are digitally encrypted and decentralized, continue to attract attention of nancial market players across the world. Because of high volatility in cryptocurrency market, predicting price of cryptocurrencies has become one of the most complicated elds in nancial markets. In...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Allameh Tabataba'i University Press
2022-07-01
|
| Series: | Mathematics and Modeling in Finance |
| Subjects: | |
| Online Access: | https://jmmf.atu.ac.ir/article_14563_6236068a080e105c29b7816d6461652d.pdf |
| _version_ | 1797796011176886272 |
|---|---|
| author | Kamran Pakizeh Arman Malek Mahya Karimzadeh khosroshahi Hasan Hamidi Razi |
| author_facet | Kamran Pakizeh Arman Malek Mahya Karimzadeh khosroshahi Hasan Hamidi Razi |
| author_sort | Kamran Pakizeh |
| collection | DOAJ |
| description | Cryptocurrencies, which are digitally encrypted and decentralized, continue to attract attention of nancial market players across the world. Because of high volatility in cryptocurrency market, predicting price of cryptocurrencies has become one of the most complicated elds in nancial markets. In this paper, we use Long Short-Term Memory (LSTM) and Gated Recurrent Unit (GRU) models to predict price of four well-known cryptocurrencies of Bitcoin (BTC), Ethereum(ETH), Litecoin (LTC), and Ripple (XRP). These models are subdivisions of Articial Intelligence, machine learning and data science. The main aim of this paper is to compare the accuracy of above-mentioned models in forecasting time series data, to nd out which model can better predict price in these four cryptocurrencies. 43 variables consisting of 28 technical indicators and t+10 lags were calculated and appended to the Open, High, Low, Close and Volume (OHLCV) data for selected cryptocurrencies. Applying random forest as feature selection, 25 variables werechosen, 24 of them selected as feature (independent variables) and one as a dependent variable. Each attribute value was converted into a relative standard score, followed by Min-max scaling; we compare models and results of Dieblod Mariano test that is used to examine whether the differences in predictive accuracy with these two models are signi cant, reveal that LSTM reaches better accuracy than GRU for BTC and ETH, but both models convey the same accuracy for LTC and XRP. |
| first_indexed | 2024-03-13T03:26:41Z |
| format | Article |
| id | doaj.art-c87588c0d2ea43c7be8215a321ae317d |
| institution | Directory Open Access Journal |
| issn | 2783-0578 2783-056X |
| language | English |
| last_indexed | 2024-03-13T03:26:41Z |
| publishDate | 2022-07-01 |
| publisher | Allameh Tabataba'i University Press |
| record_format | Article |
| series | Mathematics and Modeling in Finance |
| spelling | doaj.art-c87588c0d2ea43c7be8215a321ae317d2023-06-25T07:59:43ZengAllameh Tabataba'i University PressMathematics and Modeling in Finance2783-05782783-056X2022-07-012113210.22054/jmmf.2022.1456314563Assessing machine learning performance in cryptocurrency market price predictionKamran Pakizeh0Arman Malek1Mahya Karimzadeh khosroshahi2Hasan Hamidi Razi3Faculty of Financial Sciences, Kharazmi University, Tehran, IranFaculty of Financial Sciences, Kharazmi University, Tehran, IranFaculty of Financial Sciences, Kharazmi University, Tehran, IranFaculty of Agriculture, Tarbiat Modares University, Tehran, Iran.Cryptocurrencies, which are digitally encrypted and decentralized, continue to attract attention of nancial market players across the world. Because of high volatility in cryptocurrency market, predicting price of cryptocurrencies has become one of the most complicated elds in nancial markets. In this paper, we use Long Short-Term Memory (LSTM) and Gated Recurrent Unit (GRU) models to predict price of four well-known cryptocurrencies of Bitcoin (BTC), Ethereum(ETH), Litecoin (LTC), and Ripple (XRP). These models are subdivisions of Articial Intelligence, machine learning and data science. The main aim of this paper is to compare the accuracy of above-mentioned models in forecasting time series data, to nd out which model can better predict price in these four cryptocurrencies. 43 variables consisting of 28 technical indicators and t+10 lags were calculated and appended to the Open, High, Low, Close and Volume (OHLCV) data for selected cryptocurrencies. Applying random forest as feature selection, 25 variables werechosen, 24 of them selected as feature (independent variables) and one as a dependent variable. Each attribute value was converted into a relative standard score, followed by Min-max scaling; we compare models and results of Dieblod Mariano test that is used to examine whether the differences in predictive accuracy with these two models are signi cant, reveal that LSTM reaches better accuracy than GRU for BTC and ETH, but both models convey the same accuracy for LTC and XRP.https://jmmf.atu.ac.ir/article_14563_6236068a080e105c29b7816d6461652d.pdfcryptocurrencylong short-term memorygated recurrent unitrandom forest classifier |
| spellingShingle | Kamran Pakizeh Arman Malek Mahya Karimzadeh khosroshahi Hasan Hamidi Razi Assessing machine learning performance in cryptocurrency market price prediction Mathematics and Modeling in Finance cryptocurrency long short-term memory gated recurrent unit random forest classifier |
| title | Assessing machine learning performance in cryptocurrency market price prediction |
| title_full | Assessing machine learning performance in cryptocurrency market price prediction |
| title_fullStr | Assessing machine learning performance in cryptocurrency market price prediction |
| title_full_unstemmed | Assessing machine learning performance in cryptocurrency market price prediction |
| title_short | Assessing machine learning performance in cryptocurrency market price prediction |
| title_sort | assessing machine learning performance in cryptocurrency market price prediction |
| topic | cryptocurrency long short-term memory gated recurrent unit random forest classifier |
| url | https://jmmf.atu.ac.ir/article_14563_6236068a080e105c29b7816d6461652d.pdf |
| work_keys_str_mv | AT kamranpakizeh assessingmachinelearningperformanceincryptocurrencymarketpriceprediction AT armanmalek assessingmachinelearningperformanceincryptocurrencymarketpriceprediction AT mahyakarimzadehkhosroshahi assessingmachinelearningperformanceincryptocurrencymarketpriceprediction AT hasanhamidirazi assessingmachinelearningperformanceincryptocurrencymarketpriceprediction |