Supply chain sales forecasting based on lightGBM and LSTM combination model
| DOI | https://doi.org/10.1108/IMDS-03-2019-0170 |
| Pages | 265-279 |
| Date | 10 September 2019 |
| Published date | 10 September 2019 |
| Author | Tingyu Weng,Wenyang Liu,Jun Xiao |
| Subject Matter | Information & knowledge management |
Supply chain sales forecasting
based on lightGBM and LSTM
combination model
Tingyu Weng
University of the Chinese Academy of Sciences, Beijing, China
Wenyang Liu
Tianjin University, Tianjin, China, and
Jun Xiao
University of the Chinese Academy of Sciences, Beijing, China
Abstract
Purpose –The purpose of this paper is to design a model that can accurately forecast the supplychain sales.
Design/methodology/approach –This paper proposed a new model based on lightGBM and LSTM to
forecast the supply chain sales. In order to verify the accuracy and efficiency of this model, three
representative supply chain sales data sets are selected for experiments.
Findings –The experimental results show that the combined model can forecast supply chain sales with
high accuracy, efficiency and interpretability.
Practical implications –With the rapid development of big data and AI, using big data analysis and
algorithm technology to accurately forecast the long-term sales of goods will provide the database for the
supply chain and key technical support for enterprises to establish supply chain solutions. This paper
provides an effective method for supply chain sales forecasting, which can help enterprises to scientifically
and reasonably forecast long-term commodity sales.
Originality/value –The proposed model not only inherits the ability of LSTM model to automatically mine
high-level temporal features, but also has the advantages of lightGBM model, such as high efficiency, strong
interpretability, which is suitable for industrial production environment.
Keywords Supply chain, Deep learning, Gradient boosting machine, Sale forecast
Paper type Research paper
Highlights:
•Proposed a combined model based on lightGBM and LSTM to forecast the supply
chain sales.
•Summarizes the process of constructing the features of supply chain sales data set.
•The combined model has high accuracy, efficiency and interpretability.
1. Introduction
In recent years, the development of e-commerce and logistics industry has changed the
scope and speed of supply chain demand. In order to consolidate competitive advantages
and seize market, enterprises must respond quickly to customer demand. However, due to
the intricate social relationships and the ever-changing market demand, the uncertainty has
increased, leading to excessive costs for companies in the supply chain. How to effectively
Industrial Management & Data
Systems
Vol. 120 No. 2, 2020
pp. 265-279
© Emerald PublishingLimited
0263-5577
DOI 10.1108/IMDS-03-2019-0170
Received 24 March 2019
Revised 23 April 2019
5 July 2019
Accepted 10 August 2019
The current issue and full text archive of this journal is available on Emerald Insight at:
www.emeraldinsight.com/0263-5577.htm
This work is supported by the National Natural Science Foundation of China (No. 61471338), Youth
Innovation Promotion Association CAS (2015361), Key Research Program of Frontier Sciences
CAS (QYZDY-SSW-SYS004), Beijing Nova program (Z171100001117048) and Beijing Science and
Technology Project (Z181100003818019).
265
Supply chain
sales
forecasting
To continue reading
Request your trial