A Survey of Bayesian Decision Making
Abstract
analysis, machine learning, artificial intelligence and many application fields. It provides a probability based method to deal with uncertainty
and reflect new information by constantly updating the probability distribution. In the Bayesian decision-making framework, decision makers first set the prior probability distribution based on historical data or expert knowledge, and then update these distributions according to the
newly collected data by using Bayesian theorem to reflect the latest cognition of the current situation. The advantage of Bayesian decision is
that it can deal with uncertainty naturally, and can continuously improve the decision through continuous data collection and analysis. In addition, it can also deal with complex dependencies and uncertainty propagation, which is crucial for many practical application scenarios. Starting from the origin of Bayesian decision theory, this paper introduces its development process and research in detail, aiming to have a clear
understanding of Bayesian decision theory from a macro perspective; Then the application of Bayesian decision theory in different fields is
described; Finally, the development prospects and challenges in the future are introduced.
Keywords
Full Text:
PDFReferences
[1] Xiong Liwen Inductive logic and Bayesian method [j]. Journal of Beijing Normal University (Social Sciences Edition), 2007, (02): 143-
145.
[2] Xiong Liwen The development of modern inductive logic Beijing: People's publishing house, 2004:16.
[3] Hu Yimin On Jeffrey's decision logic [j]. logic research album, 2003, (00): 48-51.
[4] Xiong Liwen Modern development of inductive logic [j]. Journal of Beijing University of Aeronautics and Astronautics (Social Science
Edition), 2000, (02): 45-47+57. DOI:10.13766/j.bhsk.1008-2204.2000.02.011.
[5] Huzhijun, Peng Fei, lizhixia Bayesian evaluation and selection strategy for portfolio decision of venture projects [j]. China management
science, 2017, 25 (02): 30-39. doi:10.16381/j.cnki.issn1003-207x.2017.02.004.
[6] Zeng Xiaohong Extended Bayesian decision model for investment risk assessment of mobile Internet enterprises [j]. statistics and decision making, 2016, (14): 36-40. DOI:10.13546/j.cnki.tjyjc.2016.14.009.
[7] Xu Xiaoxue, zhangqingguo, Xu Li, et al Application of Bayesian decision in risk analysis of large-scale aquaculture [j]. Chinese agronomy bulletin, 2014, 30 (35): 7-12.
[8] Lu Jing, Tang Xiaowo Research on operational risk early warning mechanism based on Bayesian network [j]. Journal of management
engineering, 2008, 22 (04): 56-61.
[9] Jiahuanjun Application of Bayesian method in risk analysis of engineering construction projects [j]. mathematical statistics and management, 2005, (03): 10-14. DOI:10.13860/j.cnki.sltj.2005.03.003.
[10] Zhangjunguang, xuzhenchao Research and development project risk assessment method based on Bayesian risk decision theory [j]. industrial technology and economics, 2012, 31 (12): 66-70.
[11] Nicholson, Ann E. et al. A Case Study in Knowledge Discovery and Elicitation in an Intelligent Tutoring Application. ArXiv
abs/1301.2297 (2001): n. pag.
[12] Shaozhong, Zhang. Application of Bayesian Networks in Decision Supporting System. Computer Engineering (2004): n. pag.
[13] Liao Juan, lidehua Bayesian network inference algorithm based on message propagation and its application [j]. computer and digital engineering, 2016, 44 (01): 16-20+57.
[14] Qiu Guofang, Wang Xiaoning Research on hospital hierarchical diagnosis and treatment decision based on three branch decision [j].
Journal of Henan Normal University (Natural Science Edition), 2018, 46 (03): 106-111. doi:10.16366/j.cnki.1000-2367.2018.03.018.
DOI: http://dx.doi.org/10.70711/frim.v3i3.6184
Refbacks
- There are currently no refbacks.