Enhancing Cryptocurrency Price Forecasting Accuracy: A Feature Selection and Weighting Approach with Bi-Directional LSTM and Trend-Preserving Model Bias Correction

• Published in: IEEE access Vol. 11; p. 1
• Main Authors: Rafi, Muhammed, Hameed, Sufian, Sohail, Izaan, Aliasghar, Maria, Aziz, Arisha, Mirza, Qublai Ali Khan
• Format: Journal Article
• Language: English
• Published: Piscataway IEEE 01-01-2023; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Bias; Bitcoin; Blockchain; Blockchains; Control charts; Counterfeit; cryptocurrency; Cryptography; CUSUM charts; Data models; Digital currencies; Forecasting; Goats; Government regulations; Intervals; Long short term memory; Machine learning; Mathematical models; Predictive models; Weighting
• ISSN: 2169-3536; 2169-3536
• DOI: 10.1109/ACCESS.2023.3287888

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). Comparing with the prevalent forecasting models we report a new state of the art in cryptocurrency forecasting.