Optimizing Dynamic Programming Algorithm Based on Bayesian Model to Solve Enterprise Decision-Making Problem

DOI: https://doi.org/10.62517/jbdc.202401405

Author(s)

Haifeng Jiang, Yuchao He, Jianqiao Liang, Zhenting Chen*

Affiliation(s)

School of Artificial Intelligence, Guangzhou Huashang University, Guangzhou, Guangdong, China *Corresponding Author.

Abstract

In the current highly competitive business landscape, enterprises face a series of complex decision-making challenges during the efficient production process of popular electronic products. Taking this as the entry point, this paper deeply analyzes these problems, aiming to build a scientific theoretical foundation for enterprise decision-making, optimize the production process, reduce costs, and enhance economic benefits. This paper first uses statistical hypothesis testing to design a sampling scheme to evaluate the defective rate of parts. Then, the dynamic programming algorithm is employed, and a defective rate optimization model based on Bayesian update is incorporated to comprehensively optimize the detection and disposal decisions of parts, finished products, and defective products in the enterprise production process. The research results show that the optimization model can effectively deal with the risk of defective rate fluctuations and ensure the consistency and reliability of decision-making results. Through case analysis, it can be seen that this model can customize accurate decision-making schemes for enterprises in various scenarios and significantly improve economic benefits. In summary, this study provides crucial theoretical support and practical guidance for the improvement of enterprise management level and industrial upgrading, demonstrating significant value in practical applications.

Keywords

Bayesian Model; Enterprise Decision-Making; Dynamic Programming Algorithm; Statistical Hypothesis; Defective Rate Fluctuations

References

[1] LI Jia-rong, MEI Hua-ping, Luo Dan-yan, et al. Ordering and transportation of raw materials in manufacturing enterprises based on mathematical programming model. Heilongjiang Science, 2024, 15 (16): 77-81. [2] CuiRumai, SiShoukui. Mathematical model of data visualization processing. Journal of Naval Aeronautical Engineering College, 2010,25 (01): 105-108 + 112. [3] Jiang Qiyuan, Xie Jinxing, YeJun, Mathematical Model. 5th Edition. Beijing: Higher Education Press, 2018. [4] Yang. Analysis of the relationship among binomial distribution, Poisson distribution and normal distribution. Enterprise Science and Technology and Development, 2008, (20):108-110. [5] He Siyao, Shen Yue, Xin Yanyu. Dynamic programming algorithm for optimal solution problem. Electroacoustic Technology,2019,43(03): 42-44. DOI: 10.16311/J.Audioe.2019.03.011. [6] Li Ruijie, CuiShichang, ZhangYihan, et al. Real-time coordinated voltage regulation strategy of distribution network based on approximate dynamic programming. Power Grid Technology,1-12[2024-09-08]. Https://doi.org/10.13335/j.1000-3673.pst.2023.1996. [7] Powell W.B. Approximate dynamic programming: Solving the curses of dimensionality. Hoboken John Wiley & Sons,2007. [8] Wang Di. Research and Application of Weighted Bayesian Network Classification Algorithm. Hubei Normal University, 2024. DOI:10.27796/d.CNKI. Ghbs f. 2024. 000228. [9] Zhang Sichen, Fang Huan. Emergency decision model for hazardous chemicals leakage based on dynamic Bayes. Journal of Lanzhou Institute of Technology, 2024, 31 (04): 94-99. [10] Wang Ke, Shao Jingwen, Yang Jun. Research on landing distance of acivilaircraft based on Bayesian network. Progress in Aeronautical Engineering,1-8[2024-09-08]. http://kns.cnki.net/kcms/detail/61.1479.V. 20240719.1249.004.html.