Analysis of earnings forecast of blockchain financial products based on particle swarm optimization

【Author】 Gao, Wenyou; Su, Chang

【Source】JOURNAL OF COMPUTATIONAL AND APPLIED MATHEMATICS

【影响因子】2.872

【Abstract】The purpose of this study is to solve the problems of large number of iterations, limitations and poor fitting effect of traditional algorithms in predicting the yield rate of blockchain financial products. In this study, bitcoin yield rate is taken as the research object, and data from June 2, 2016 to December 30, 2018 are collected, totaling 943 pieces. The BP neural network, support vector regression machine algorithm and particle swarm optimization least square vector algorithm are respectively adopted to carry out model simulation and empirical analysis on the collected data, and it is concluded that particle swarm optimization least square vector algorithm has the best fitting effect. Subsequently, the Ethereum (ETH) yield rate is selected as the research object, and the model simulation and empirical analysis are carried out on it, which verifies that the optimized algorithm has better prediction and fitting on the time series. The results show that the particle swarm optimization algorithm among the three algorithms mentioned in this research has the best prediction effect. Therefore, the results of this study have a good fitting effect on the prediction of the yield rate of blockchain financial products, have a good guiding effect on the investors of blockchain financial products, and have a good guiding significance for the study of the yield rate of China's blockchain financial products. (C) 2020 Elsevier B.V. All rights reserved.

【Keywords】Particle swarm optimization; Blockchain; Financial product; Earnings

【发表时间】2020 JUL

【收录时间】2022-01-02

【文献类型】

【主题类别】

--