nav emailalert searchbtn searchbox tablepage yinyongbenwen piczone journalimg journalInfo journalinfonormal searchdiv searchzone qikanlogo popupnotification paper paperNew
2023, 05, v.44 10-17
基于Attention-GRU-GAN神经网络的亚马逊平台下电商公司销量预测
基金项目(Foundation): 2022年度福建省中青年教师教育科研项目(JAT220311)
邮箱(Email): 1308298184@qq.com;
DOI: 10.19724/j.cnki.jmju.2023.05.002
投稿时间: 2023-01-06
投稿日期(年): 2023
修回时间: 2023-03-06
终审时间: 2023-09-20
终审日期(年): 2023
审稿周期(年): 1
发布时间: 2023-09-25
出版时间: 2023-09-25
移动端阅读
摘要:

为提升电商平台商家备货效率,构建了一种适用于亚马逊跨境电商平台的销量预测模型,通过对某类型商品历史销量数据、产品特征数据以及产品的增量数据等一系列输入进行训练学习。该模型通过对GAN(generative adversarial network)网络、GRU(gate recurrent unit)网络以及注意力机制的结合使用,使其具备更高的预测准确率,同时通过增量式学习策略,在保证预测准确率的前提下使得模型训练时间大为缩短,为商家对商品的库存规划提供了一定的指导。

Abstract:

In order to improve the stocking efficiency of e-commerce platform merchants, a sales prediction model suitable for Amazon cross-border e-commerce platform is constructed, and trains and learns through a series of inputs such as historical sales data, product feature data, and product incremental data of a certain type of commodity.The combination of GAN(generative adversarial network)network, GRU(gate recurrent unit)network and attention mechanism enables the model to have a higher prediction accuracy rate.At the same time, through incremental learning strategy, the model training time is greatly shortened on the premise of ensuring the prediction accuracy rate, which provides certain guidance for businesses to plan the inventory of goods.

参考文献

[1] BARTHOLOMEW D J.Time series analysis forecasting and control[J].Journal of the Operational Research Society,1971,22(2):199-201.

[2] DUA P M,MILLER S M,SMYTHD J.Using leading indicators to forecast U.S.home sales in a Bayesian vector autoregressive framework[J].The Journal of Real Estate Finance and Economics,1999,18(2):191-205.

[3] VAN CALSTER T,BAESENS B,LEMAHIEU W.ProfARIMA:a profit-driven order identification algorithm for ARIMA models in sales forecasting[J].Applied Soft Computing,2017,60:775-785.

[4] LIU Y.Word of mouth for movies:its dynamics and impact on box office revenue[J].Journal of Marketing,2006,70(3):74-89.

[5] HAN W B.Effects of user reviews and critic rating on online healthcare sales[J].American Journalof Industrialand Business Management,2020,10:1 902-1 915.

[6] CHINTAGUNTA P K,GOPINATH S,VENKATARAMAN S.The effects of online user reviews on movie box office performance:accounting for sequential rollout and aggregation across local markets[J].Marketing Science,2010,29(5):944-957.

[7] 王建伟.基于商品聚类的电商销量预测[J].计算机系统应用,2016,25(10):162-168.

[8] 杨东红.基于改进BP神经网络的新能源汽车销量预测[J].自动化与仪器仪表,2021(11):60-63.

[9] LIHONG W.Forecast model of short-term sales in e-commerce based on BP-AdaBoost[J].Computer Systems & Applications,2021,30(2):260-264.

[10] 孙静.面向情报大数据的决策树增量学习算法研究[D].哈尔滨:哈尔滨工程大学,2017.

[11] 孟亮,孟京.我国跨境电商企业海外仓模式选择分析:基于消费品出口贸易视角[J].中国流通经济,2017,31(6):37-44.

[12] LIU F G,ZHANG Z W,ZHOU R L.Automatic modulation recognition based on CNN and GRU[J].Tsinghua Science and Technology,2022,27(2):422-431.

[13] HE Q Q,WU C Y,SI Y W.LSTM with particle Swam optimization for sales forecasting[J].Electronic Commerce Researchand Applications,2022,51:101 118.

[14] 宋瑞蓉,路树华,王斌君,等.基于ABiLSTM与XGBoost组合模型的交通时间预测[J].软件导刊,2021,20(8):20-28.

[15] 冯斌,郭亦宗,陈页,等.基于GRU多步预测技术的云储能充放电策略[J].电力系统自动化,2021,45(9):46-54.

[16] 牛红丽,赵亚枝.利用Bagging算法和GRU模型预测股票价格指数[J].计算机工程与应用,2022,58(12):132-138.

[17] LI Y C,WANG Q Z,ZHANG J,et al.The theoretical research of generative adversarial networks:an overview[J].Neurocomputing,2021,435:26-41.

基本信息:

DOI:10.19724/j.cnki.jmju.2023.05.002

中图分类号:TP183;F713.36;F274

引用信息:

[1]刘华锐,颜胜男,郭仕忠,等.基于Attention-GRU-GAN神经网络的亚马逊平台下电商公司销量预测[J].闽江学院学报,2023,44(05):10-17.DOI:10.19724/j.cnki.jmju.2023.05.002.

基金信息:

2022年度福建省中青年教师教育科研项目(JAT220311)

投稿时间:

2023-01-06

投稿日期(年):

2023

修回时间:

2023-03-06

终审时间:

2023-09-20

终审日期(年):

2023

审稿周期(年):

1

发布时间:

2023-09-25

出版时间:

2023-09-25

检 索 高级检索

引用

GB/T 7714-2015 格式引文
MLA格式引文
APA格式引文