Home About Login Current Archives Announcements Editorial Board
Submit Now For Authors Call for Submissions Statistics Contact
Home > Archives > Volume 16, No 6 (2018) > Article

DOI: 10.14704/nq.2018.16.6.1608

Inventory Prediction Based on Backpropagation Neural Network

Lichuan Gu, Yueyue Han, Chengji Wang, Guiyang Shu, Juanjuan Feng, Chao Wang


This paper aims to develop an effective way to predict the inventory demand of agricultural materials. Focusing on the demand of agricultural pesticide, the author introduced the backpropagation neural network (BPNN) and optimized the BPNN inventory prediction model by multiple interpolation method. In this way, a novel inventory prediction strategy was created, with the national macro policy, the pest and disease resistance, the market role and other factors as part of the BPNN. For the lack of input samples, the multiple interpolation method was adopted to restore the missing data. Then, the replacement values were combined in different ways to reveal the variation pattern of prediction error, making it possible to predict the exact pesticide demand. The research provides the decision support for inventory management in agricultural materials enterprises.


Agricultural Materials, Inventory Prediction, Backpropagation Neural Network (BPNN), Multiple Interpolation

Full Text



Fan ZY. The Algorithm and Model of BP Neural Network. Software Guide 2011; 10(7): 66-68.

Jiang S. Application of PSO-BP Neural Network in Prediction of Safety Stock in Coal Mine Machinery Enterprise. Coal Technology 2017; 2017(10): 305-07.

Liu JJ. Study on safety stock forecasting for China retail enterprises based on BP neural network. Logistics Technology 2012; 31(21): 326-29.

Liu T, Tiancang DU. Research on Inventory Prediction of Welded Pipe Plant Based on BP Neural Network. Journal of Beijing Institute of Petrochemical Technology 2017; 25(3): 53-57.

Mai J, Zhu Q, Wu D, Xie Y, Wang L. Back propagation neural network dehazing. Robotics and Biomimetics (ROBIO), 2015 IEEE International Conference on IEEE, 2015(40): 1433-38.

Pang XS. A Comparative research on method of missing data interpolation processing. Statistics and Decision 2012; 2012(24): 18-22.

Shu F, Tang QY, Shao ZR, Shi S, Cheng JA. Analyze influence factors of pesticide application of China. Agrochemicals 2010; 49(4): 241-45.

Spoorthy S, Thaskani S, Sood A, Chandra MG, Balamuralidhar P. Missing data ınterpolation using compressive sensing: An application for sales data gathering. Machine Intelligence and Signal Processing 2016; 2016(390): 27-35.

Thomassey S, Happiette M. A neural clustering and classification system for sales forecasting of new apparel items. Applied Soft Computing 2007; 7(4): 1170-87.

Wu T. Design and research on e-commerce system for agricultural commodities. University of Science and Technology of China, 2014.

Yang JW. Prediction of Regional Logistics based on GM/BP neural network Prediction model. Central South University, 2011.

Yuan J, Yu S. Privacy preserving back-propagation neural network learning made practical with cloud computing. IEEE Transactions on Parallel and Distributed Systems 2014; 25(1): 212-21.

Zhou H, Ding DY, Yi-Lin LI, Meng-Jie WU. Research on inventory demand forecast based on BP neural network. Information Technology 2016; 11: 38-41.