The impact of stock market price Fourier transform analysis on the Gated Recurrent Unit classifier model

作者：

Highlights：

• We apply Fourier transformation to extract new features from the limit order book.

• Selecting features with respect to the proposed methods improves model performance.

• Extracting Fourier based features improves the model F1 score.

摘要

•We apply Fourier transformation to extract new features from the limit order book.•Selecting features with respect to the proposed methods improves model performance.•Extracting Fourier based features improves the model F1 score.

论文关键词：Limit Order Book,Recurrent Neural Networks,Technical indicators,Fourier transform

论文评审过程：Available online 19 May 2020, Version of Record 5 June 2020.

论文官网地址：https://doi.org/10.1016/j.eswa.2020.113565