A forecasting method of pharmaceutical sales based on ARIMA-LSTM model

被引：8

作者：

Han, Yuxuan ^{[1
]}

机构：

[1] Wuhan Univ Technol, Sch Management, Wuhan, Peoples R China

来源：

2020 5TH INTERNATIONAL CONFERENCE ON INFORMATION SCIENCE, COMPUTER TECHNOLOGY AND TRANSPORTATION (ISCTT 2020) | 2020年

关键词：

-Sale forecasting; ARIMA; LSTM; Combined model;

D O I：

10.1109/ISCTT51595.2020.00064

中图分类号：

TP301 [理论、方法];

学科分类号：

081202 ;

摘要：

In order to improve the accuracy of sales forecasting for manufacturing companies, a combined forecasting method based on ARIMA model and long and short term memory (LSTM) neural network is proposed. ARIMA and LSTM are used to process the linear and nonlinear components of the sales time series, and then the prediction results are trained by the second LSTM model to obtain the final prediction. The results show that the combined model has a higher predictive precision and a wider range of applications.

引用

页码：336 / 339

页数：4

共 8 条

[1]

Ge N., 2019, COMPUTER SCI, V46, P406

[2]

Jie Wang, 2009, POWER SYSTEM PROTECT, V37, P48

[3]

Jin L., 2018, APPL RES SVM NEURAL

[4]

[刘浩然 Liu Haoran], 2016, [仪器仪表学报, Chinese Journal of Scientific Instrument], V37, P1573

[5]

Sun R. Q., 2016, Research on the Price Trend Prediction Model of American Stock Index Based on LSTM Neural Network

[6]

Wang C., 2009, POWER SYSTEM PROTECT, V37, P48

[7]

Wu L., 2016, SHANGHAI PHARM, V37, P68

[8]

Zhang Y. H., 2017, Electr. Power Inf. Commun. Technol, V15, P19

← 1 →