中国邮电高校学报(英文版) ›› 2022, Vol. 29 ›› Issue (5): 92-98.doi: 10.19682/j.cnki.1005-8885.2022.0018

• Artificial Intelligence • 上一篇    下一篇

FS-LSTM: sales forecasting in e-commerce on feature selection

张函1,井音吉2,赵永利2   

  1. 1. 金华职业技术学院
    2. 北京邮电大学
  • 收稿日期:2021-11-29 修回日期:2022-06-29 出版日期:2022-10-31 发布日期:2022-10-28
  • 通讯作者: 张函 E-mail:20141039@jhc.edu.cn

FS-LSTM: sales forecasting in e-commerce on feature selection

Zhang Han1, Jing Yinji2, Zhao Yongli2   

  • Received:2021-11-29 Revised:2022-06-29 Online:2022-10-31 Published:2022-10-28
  • Contact: Han ZHANG E-mail:20141039@jhc.edu.cn

摘要:


There are many studies on sales forecasting in e-commerce, most of which focus on how to forecast sales volume with related e-commerce operation data. In this paper, a deep learning method named FS-LSTM was proposed, which combines long short-term memory (LSTM) and feature selection mechanism to forecast the sales volume. The indicators with most contributions by the extreme gradient boosting (XGBoost) model are selected as the input features of LSTM model. FS-LSTM method can get less mean average error (MAE) and mean squared error (MSE) in the forecasting of e-commerce sales volume, comparing with the LSTM model without feature selection. The results show that the FS-LSTM can improve the performance of original LSTM for forecasting the sales volume.


关键词: sales forecasting| time series forecasting| deep learning| feature selection

Abstract:

There are many studies on sales forecasting in e-commerce, most of which focus on how to forecast sales volume with related e-commerce operation data. In this paper, a deep learning method named FS-LSTM was proposed, which combines long short-term memory (LSTM) and feature selection mechanism to forecast the sales volume. The indicators with most contributions by the extreme gradient boosting (XGBoost) model are selected as the input features of LSTM model. FS-LSTM method can get less mean average error (MAE) and mean squared error (MSE) in the forecasting of e-commerce sales volume, comparing with the LSTM model without feature selection. The results show that the FS-LSTM can improve the performance of original LSTM for forecasting the sales volume.

Key words: sales forecasting| time series forecasting| deep learning| feature selection

中图分类号: