Enhancing cryptocurrency price forecasting accuracy: a feature selection and weighting approach with bi-directional LSTM and trend-preserving model bias correction

Rafi, Muhammed, Ali Mirza, Qublai Khan ORCID: 0000-0003-3403-2935, Sohail, Muhammad Izaan, Aliasghar, Maria, Aziz, Arisha and Hameed, Sufian (2023) Enhancing cryptocurrency price forecasting accuracy: a feature selection and weighting approach with bi-directional LSTM and trend-preserving model bias correction. IEEE Access, 11. pp. 65700-65710. doi:10.1109/ACCESS.2023.3287888

Text (Published version)
12951 ALI MIRZA Qublai (2023) Enhancing cryptocurrency price forecasting accuracy article.pdf - Published Version
Available under License Creative Commons Attribution Non-commercial No Derivatives 4.0.

Download (1MB) | Preview


A cryptocurrency is a digitized, encrypted, and decentralized virtual currency, which is impossible to counterfeit or double-spend. It is one of the very popular investment instruments and traded in blockchain based crypto exchanges on ever growing volume. It is quite volatile due to imbalance of supply and demand, government regulations, investor sentiment and above all media hype. Cryptocurrency price forecasting is an active area of research and several approaches have been proposed recently. This study proposed a price forecasting model based on three vital characteristics (i) a feature selection and weighting approach based on Mean Decrease Impurity(MDI) features. (ii) Bi-directional LSTM and (iii) with a trend preserving model bias correction (CUSUM control charts for monitoring the model performance over time) to forecast Bitcoin and Ethereum values for long and short term spans. The data for both currencies were analyzed in three different intervals: (i) April 01, 2013 to April 01, 2016 (ii) April 01, 2013 to April 01, 2017 and (iii) April 01, 2013 to December 31, 2019. Extensive series of experiments were performed and evaluated on Root Mean Square Errors (RMSE). For bitcoin forecasting, the model achieved RMSE values 3.499 for interval 1, 5.070 for interval 2 and 6.642 for interval 3. Similarly, for Ethereum RSME of 0.094, 0.332, 3.027 are obtained for the three intervals respectively, On a new test-set collected from January 01, 2020 to January 01, 2022 for the two cryptocurrencies we obtained an average RSME of 9.17, with model bias correction, Comparing with the prevalent forecasting models we report a new state of the art in cryptocurrency forecasting.

Item Type: Article
Article Type: Article
Uncontrolled Keywords: Blockchain; Cryptocurrency; Machine learning
Subjects: H Social Sciences > HG Finance > HG4501 Investment, capital formation, speculation
Q Science > QA Mathematics > QA76 Computer software
Divisions: Schools and Research Institutes > School of Business, Computing and Social Sciences
Research Priority Areas: Applied Business & Technology
Depositing User: Rhiannon Goodland
Date Deposited: 19 Jul 2023 11:56
Last Modified: 04 Dec 2023 12:30
URI: https://eprints.glos.ac.uk/id/eprint/12951

University Staff: Request a correction | Repository Editors: Update this record

University Of Gloucestershire

Bookmark and Share

Find Us On Social Media:

Social Media Icons Facebook Twitter Google+ YouTube Pinterest Linkedin

Other University Web Sites

University of Gloucestershire, The Park, Cheltenham, Gloucestershire, GL50 2RH. Telephone +44 (0)844 8010001.