基于大数据的智能风险防控平台设计与实现

章明, 刘培

中国工程科学 ›› 2020, Vol. 22 ›› Issue (6) : 111-120.

PDF(963 KB)
PDF(963 KB)
中国工程科学 ›› 2020, Vol. 22 ›› Issue (6) : 111-120. DOI: 10.15302/J-SSCAE-2020.06.015
网络空间安全保障战略研究
Orginal Article

基于大数据的智能风险防控平台设计与实现

作者信息 +

Design and Implementation of Intelligent Risk Control Platform Based on Big Data

Author information +
History +

摘要

金融安全是国家安全的重要组成部分,防范化解金融风险是金融工作的根本性任务。为帮助商业银行加快打造适应数字经济时代发展需要的风险防控平台,本文基于大数据应用的关键技术,提出了一种 “五层两域”智能风险防控平台总体框架;纵向包含风险数据层、特征计算层、风险模型层、决策引擎层、业务接入层,各层之间松耦合、无状态、可扩展;横向则划分为生产部署域、业务运营域,可最大程度兼顾系统运行的稳定性与业务应用的灵活度。该设计有助于商业银行实现风险数据的统一治理和统一管理,在保证风险防控平台高效稳定运行的同时,又能在风险防控运营、数据分析、模型设计、规则调整等方面为风险防控业务人员提供充足的支撑。以某金融机构部署的智能风险防控平台为例,阐述了该平台的应用情况及实际成效,并对智能风险防控平台的应用发展提出建议。

Abstract

Since financial security is an important part of national security, controlling financial risks is the fundamental task for financial management. To help banks accelerate the establishment of risk control platforms in the era of digital economy, this study proposes an overall framework of an intelligent risk control platform with “five layers and two domains” based on the key technologies of big data. Specifically, the framework vertically consists of a risk data layer, a feature computing layer, a risk model layer, a decision engine layer, and a business access layer and all these layers are loosely coupled, stateless, and extensible. Horizontally, the framwork can be divided into a production deployment domain and a business operation domain, which considers both the stability of system operation and flexibility of business application. This design is helpful for commercial banks to realize the unified governance and management of risk data. While ensuring the efficient and stable operation of the risk control platform, it can also provide sufficient support for risk control experts in risk control operation, data analysis, model design, and rule adjustment. Finally, using the intelligent risk control platform deployed by a financial institution as an example, this study expounds the application situation and practical effect of the platform and provides some suggestions.

关键词

风险防控 / 大数据 / 机器学习 / 实时计算 / 金融行业

Keywords

risk control / big data / machine learning / real-time computation / financial industry

引用本文

导出引用
章明, 刘培. 基于大数据的智能风险防控平台设计与实现. 中国工程科学. 2020, 22(6): 111-120 https://doi.org/10.15302/J-SSCAE-2020.06.015

参考文献

[1]
刘刚. 大数据时代智能风控体系建设实践 [J]. 中国金融电脑, 2018, 349(8): 17–20. Liu G. Practice of intelligent risk control system construction in the era of big data [J]. China Financial Computer, 2018, 349(8): 17–20.
[2]
陈稀. 基于深度学习的智能风控系统 [D]. 北京: 北京交通大学 (硕士学位论文), 2019. Chen X. Intelligent risk control system based on deep learning [D]. Beijing: Beijing Jiaotong University(Master’s thesis), 2019.
[3]
丁世博. 基于SOA的安全风控平台研究与设计 [D]. 西安: 西安 电子科技大学(硕士学位论文), 2018. Ding S B. Research and design of security risk control platform based on SOA [D]. Xi’an: Xidian University(Master’s thesis), 2018.
[4]
张鲁男, 常宝岗, 梅利. 基于规则引擎及智能阈值的实时业务风 控系统 [J]. 通信技术, 2019, 52(11): 2720–2724. Zhang L N, Chang B G, Mei L. Real-time business risk control system based on rule engine and intelligent threshold [J]. Communication Technology, 2019, 52(11): 2720–2724.
[5]
郭锐. T公司大数据风险防控平台的研究 [D]. 南京: 南京大学 (硕士学位论文), 2016. Guo R. Research on T Company’s big data risk control platform [D]. Nanjing: Nanjing University(Master`s thesis), 2016.
[6]
王欣. 基于人工智能的移动金融风险防控体系建设中的实践 [J]. 信息安全研究, 2017, 3(11): 1000–1005. Wang X. Practice of mobile financial risk control system construction based on artificial intelligence [J]. Information Security Research, 2017, 3(11): 1000–1005.
[7]
坚决打好防范化解重大风险攻坚战 [J]. 实践, 2018 (6): 18–19. Fight resolutely to prevent and defuse major risks [J]. Practice, 2018 (6): 18–19.
[8]
刘瑞霞. 打造基于大数据的智能化风险防控体系 [J]. 金融电子 化, 2018 (8): 57–58. Liu R X. Building an intelligent risk control system based on big data [J]. Electronic Finance, 2018 (8): 57–58.
[9]
宫夏屹, 李伯虎, 柴旭东, 等. 大数据平台技术综述 [J]. 系统仿 真学报, 2014, 26(3): 489–496. Gong X Y, Li B H, Chai X D, et al. Overview of big data platform technology [J]. Journal of System Simulation, 2014, 26(3): 489– 496.
[10]
Jiang C, Ding Z , Wang J, et al. Big data resource service platform for the internet financial industry [J]. Chinese Science Bulletin, 2014, 59(35): 5051–5058.
[11]
刘智慧, 张泉灵. 大数据技术研究综述 [J]. 浙江大学学报: 工学 版, 2014, 48(6): 957–972. Liu Z H, Zhang Q L. Research review of big data technology [J]. Journal of Zhejiang University: Engineering, 2014, 48(6): 957–972.
[12]
Borthakur D. HDFS architecture guide [J]. Hadoop Apache Project, 2008, 53(1–13): 2.
[13]
Dean J, Ghemawat S. MapReduce: Simplified data processing on large clusters [J]. Communications of the ACM, 2008, 51(1): 107–113.
[14]
宋杰, 孙宗哲, 毛克明, 等. MapReduce大数据处理平台与算法 研究进展 [J]. 软件学报, 2017, 28 (3): 514–543. Song J, Sun Z Z, Mao K M, et al. Research advance on MapReduce based big data processing platforms and algorithms [J]. Journal of software, 2017, 28(3): 514–543.
[15]
孙大为, 张广艳, 郑纬民. 大数据流式计算: 关键技术及系统实 例 [J]. 软件学报, 2014 (4): 153–176. Sun D W, Zhang G Y, Zheng W M. Big data streaming calculation: Key technologies and system examples [J]. Journal of software, 2014 (4): 153–176.
[16]
Katsifodimos A, Schelter S. Apache flink: Stream analytics at scale [C]. Berlin: IEEE International Conference on Cloud Engineering Workshop (IC2EW), 2016: 193.
[17]
吴璨, 王小宁, 肖海力, 等. 分布式消息系统研究综述 [J]. 计算 机科学, 2019 (S1): 1–5. Wu C, Wang X N, Xiao H L, et al. Research review of distributed message system [J]. Computer Science, 2019 (S1): 1–5.
[18]
黄健宏. Redis设计与实现 [M]. 北京: 机械工业出版社, 2014. Huang J H. Design and implementation of Redis [M]. Beijing: China Machine Press, 2014.
[19]
何清, 李宁, 罗文娟, 等. 大数据下的机器学习算法综述 [J]. 模 式识别与人工智能, 2014 (4): 327–336. He Q, Li N, Luo W J, et al. A survey of machine learning algorithms for big data [J]. Pattern Recognition and Artificial Intelligence, 2014 (4): 327–336.
基金
中国工程院咨询项目“网络空间安全保障战略研究”(2017-XY-45)
PDF(963 KB)

Accesses

Citation

Detail

段落导航
相关文章

/