Altcoins Talks - Cryptocurrency Forum
Cryptocurrency Ecosystem => Other Popular Cryptos / Coins => Polkadot Forum => Topic started by: Goldlife on April 06, 2021, 04:02:50 PM
-
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.
University, Qatar. She received her B.Tech (I.T) from Anna University and M.E (CSE) from St.Peters University. She has obtained her PhD in the area of information security from Anna University, Chennai. Her research interest is also extended in the areas of network analysis using Cloud Computing, and Information Security.
Ashutosh Sharma is currently working as Assistant Prof. in School of Electronics and Communication Engineering at Lovely Professional University, India. He has completed his Ph.D. and M.Tech. in ECE from JUIT, India in 2019 and 2016, respectively. His topics of interest in research are SLA and QoS in communication, risk analysis, VANET, UAV, cloud computing, and machine learning.
More info: https://www.sciencedirect.com/science/article/abs/pii/S0045790618331343