Pattern recognition in financial surveillance with the ARMA-GARCH time series model using support vector machine

作者：

Highlights：

• An auto-correlated financial process is monitored.

• A new method based on SVM is proposed to detect upward and downward shifts.

• A new feature is proposed for the better distinction of step and trend shift patterns.

• A comprehensive simulation study is performed to evaluate the performance.

• The proposed approach is applied to classify patterns in two real cases.

摘要

•An auto-correlated financial process is monitored.•A new method based on SVM is proposed to detect upward and downward shifts.•A new feature is proposed for the better distinction of step and trend shift patterns.•A comprehensive simulation study is performed to evaluate the performance.•The proposed approach is applied to classify patterns in two real cases.

论文关键词：Financial surveillance,Pattern recognition,Support vector machine,Feature extraction,OPEC crude oil basket return,Tehran Stock Exchange Index

论文评审过程：Received 11 December 2019, Revised 13 April 2021, Accepted 1 June 2021, Available online 5 June 2021, Version of Record 12 June 2021.

论文官网地址：https://doi.org/10.1016/j.eswa.2021.115334