Prediction of the price of Ethereum blockchain cryptocurrency in an industrial finance system. (January 2020)

• Record Type: Journal Article
• Authors: M., Poongodi; Sharma, Ashutosh; V., Vijayakumar; Bhardwaj, Vaibhav; Sharma, Abhinav Parkash; Iqbal, Razi; Kumar, Rajiv
• Is Part Of: Computers & electrical engineering. Volume 81(2020)
• Publication Date: 2020-01
• Subjects: Linear regression -- SVM -- Cryptocurrency -- Ether -- Industrial finance system; Computer engineering -- Periodicals; Electrical engineering -- Periodicals; Electrical engineering -- Data processing -- Periodicals; Ordinateurs -- Conception et construction -- Périodiques; Électrotechnique -- Périodiques; Électrotechnique -- Informatique -- Périodiques; Computer engineering; Electrical engineering; Electrical engineering -- Data processing; Periodicals; Electronic journals; 621.302854
• DOI: 10.1016/j.compeleceng.2019.106527
• Languages: English
• ISSNs: 0045-7906

Abstract

Abstract: Cryptocurrency has gained considerable popularity in the past decade. The untraceable and uncontrolled nature of cryptocurrency attracts millions of people around the world. Research in cryptocurrency is dedicated to finding the ether and predicting its price according to the cryptocurrency's past price inflations. In this study, price prediction is performed with two machine learning methods, namely linear regression (LR) and support vector machine (SVM), by using a time series consisting of daily ether cryptocurrency closing prices. Different window lengths are used in ether cryptocurrency price prediction by using filters with different weight coefficients. In the training phase, a cross-validation method is used to construct a high-performance model independent of the data set. The proposed model is implemented using two machine learning techniques. When using the proposed model, the SVM method has a higher accuracy (96.06%) than the LR method (85.46%). Furthermore, the accuracy score of the proposed model can be increased up to 99% by adding features to the SVM method.