Application of Long Short-Term Memory Neural Network to Sales Forecasting in Retail-A Case Study

被引：9

作者：

Yu, Quan ^{[1
]}

Wang, Kesheng ^{[1
]}

Strandhagen, Jan Ola ^{[1
]}

Wang, Yi ^{[2
]}

机构：

[1] Norwegian Univ Sci & Technol, Dept Mech & Ind Engn, Trondheim, Norway

[2] Plymouth Univ, Sch Business, Plymouth, Devon, England

来源：

ADVANCED MANUFACTURING AND AUTOMATION VII | 2018年 / 451卷

关键词：

Deep learning; LSTM; RNN; Sales forecasting; LSTM;

D O I：

10.1007/978-981-10-5768-7_2

中图分类号：

TP [自动化技术、计算机技术];

学科分类号：

0812 ;

摘要：

Sales forecasting is an important task for managers to make replenishment according to historical sales. A flexible and easy to use forecasting solution will benefit retailers from loss of sale, over supply and merchandise waste. Deep learning is a popular topic in many fields in recent years. This paper tests a long short-term memory (LSTM) recurrent neural networks (RNN) on 45 weeks point of sale (POS) data of 66 products without considering the impact of seasonality and promotions. One fourth of products have a relatively low forecasting error, which validates the feasibility of the LSTM network to some degree.

引用

页码：11 / 17

页数：7

共 7 条

[1]

Bakker B, 2002, 2002 IEEE/RSJ INTERNATIONAL CONFERENCE ON INTELLIGENT ROBOTS AND SYSTEMS, VOLS 1-3, PROCEEDINGS, P938, DOI 10.1109/IRDS.2002.1041511

[2]

Economist Intelligence Unit, 2012, DAT VERS INST PERF G

[3]

Gers FA, 2001, LECT NOTES COMPUT SC, V2130, P669

[4]

Gonzalez-Dominguez J., 2014, P INT 2014 SING 1418, P2155, DOI DOI 10.21437/INTERSPEECH.2014-483

[5]

Greff K., 2015, Lstm: A search space odyssey

[6]

Hochreiter S, 1997, NEURAL COMPUT, V9, P1735, DOI [10.1162/neco.1997.9.8.1735, 10.1007/978-3-642-24797-2, 10.1162/neco.1997.9.1.1]

[7] Multi-stream LSTM-HMM decoding and histogram equalization for noise robust keyword spotting [J].

Woellmer, Martin ;

Marchi, Erik ;

Squartini, Stefano ;

Schuller, Bjoern .

COGNITIVE NEURODYNAMICS, 2011, 5 (03) :253-264

← 1 →