Data decomposition based fast reduced kernel extreme learning machine for currency exchange rate forecasting and trend analysis
作者：
Highlights：
• Kernel Extreme Learning Machine (KELM) is used to forecast Currency Exchange rate and Trend.
• A fast reduced version of KELM reduces execution time using random support vectors from the data.
• Nonlinear time series data is first decomposed by Empirical Mode decomposition.
• Accurate forecasting and trend analysis is achieved for a basket of currencies.
• The currency movement trends are used to generate trading signals using KELM.
摘要
•Kernel Extreme Learning Machine (KELM) is used to forecast Currency Exchange rate and Trend.•A fast reduced version of KELM reduces execution time using random support vectors from the data.•Nonlinear time series data is first decomposed by Empirical Mode decomposition.•Accurate forecasting and trend analysis is achieved for a basket of currencies.•The currency movement trends are used to generate trading signals using KELM.
论文关键词：Kernel Fast reduced Extreme Learning Machine,Kernel functions,Empirical mode decomposition,Currency exchange rate forecasting,Trend and Trading analysis
论文评审过程：Received 17 May 2017, Revised 20 September 2017, Accepted 26 October 2017, Available online 27 October 2017, Version of Record 5 January 2018.
论文官网地址：https://doi.org/10.1016/j.eswa.2017.10.053
