China’s commercial bank stock price prediction using a novel K-means-LSTM hybrid approach

作者：

Highlights：

• DTW-Kmeans is an effective time series clustering model for banks' stock prices.

• The accuracy of prediction is improved by integrating clustering and LSTM.

• The performance of long term prediction is improved by multi-step prediction.

• The data of 16 major listed banks in China make the model an investment reference.

摘要

•DTW-Kmeans is an effective time series clustering model for banks' stock prices.•The accuracy of prediction is improved by integrating clustering and LSTM.•The performance of long term prediction is improved by multi-step prediction.•The data of 16 major listed banks in China make the model an investment reference.

论文关键词：Commerical Bank,Stock price prediction,K-means,DTW,LSTM neural network,Hybrid model

论文评审过程：Received 20 August 2021, Revised 27 December 2021, Accepted 25 April 2022, Available online 29 April 2022, Version of Record 5 May 2022.

论文官网地址：https://doi.org/10.1016/j.eswa.2022.117370