大数据 ›› 2021, Vol. 7 ›› Issue (3): 116-129.doi: 10.11959/j.issn.2096-0271.2021029

• 专题:基于大数据的知识图谱及其应用 • 上一篇    下一篇

基于金融知识图谱的会计欺诈风险识别方法

陈强1, 代仕娅2   

  1. 1 兴业银行信息科技部,上海 201201
    2 蚂蚁科技国际事业群数据算法技术部,上海 200120
  • 出版日期:2021-05-15 发布日期:2021-05-01
  • 作者简介:陈强(1976- ),男,博士,兴业银行信息科技部创新技术总监、高级工程师、高级经济师,厦门大学统计学与数据科学系兼职教授,中国计算机学会(CCF)会员,北京金融科技产业联盟人工智能专业委员会委员,兴业银行集团科技架构专家委员会常任委员。主要研究方向为数据科学,人工智能算法在金融风险控制、财富管理、理财投资等业务领域的应用研发及系统落地。
    代仕娅(1990- ),女,蚂蚁科技国际事业群数据算法技术部数据产品专家,主要研究方向为数据科学、人工智能相关产品在金融领域的研发及落地应用。
  • 基金资助:
    2018年上海市人工智能创新发展专项资金资助项目(XX-RGZN-01-18-9814);2020年中国计算机用户协会金融信息科技风险管理及审计领域最佳实践入库项目;2019年国家互联网数据中心产业技术创新战略联盟(NIISA)技术创新二等奖项目

Recognition method of accounting fraud risk based on financial knowledge graph

Qiang CHEN1, Shiya DAI2   

  1. 1 Information and Technology Department, Industrial Bank Co., Ltd., Shanghai 201201, China
    2 Data and Algorithm Department, Ant Technology International Business Group, Shanghai 200120, China
  • Online:2021-05-15 Published:2021-05-01
  • Supported by:
    2018 Shanghai Artificial Intelligence Innovation and Development Project Supported by Special Fundation(XX-RGZN-01-18-9814);2020 Best Practice Project in Financial Information Technology Risk Management and Audit Field Sponsored by China Computer Users Association;2019 Second Prize of Technology Innovation Sponsored by National Internet Data Center Industrial Technology Innovation Strategic Alliance(NIISA)

摘要:

针对商业银行会计案件日益复杂且频发的问题,将会计案防领域的行业知识与金融知识图谱技术结合,以更精准地识别与防范商业银行会计风险。采用图分析、图挖掘等技术,提取深层关联风险特征,并与行业经验知识相结合,构建了249条单点规则及425条组合规则,形成了丰富、可灵活配置的反欺诈策略体系。将该智能化反欺诈方法应用于银行活期账户的风险排查,与传统规则策略相比,识别精准度大幅提升,且对于筛选出的高度可疑账户,识别精准度达到85%左右,极大提升了会计案件核查的效率。

关键词: 会计案防, 金融知识图谱, 反欺诈, 关联交易

Abstract:

Since the accounting risk events exhibit complexity increasingly and occur frequently, a method merged by industrial knowledge and financial knowledge graph was proposed to recognize and prevent commercial bank's accounting risk more precisely.Based on the financial knowledge graph of account transaction, deep graph connected risk features were extracted via various graph analysis and mining technologies.Combining the graph features with industrial knowledge, 249 single rules and 425 assembled rules were constructed to form a more affluent and flexibly configurable anti-fraud strategy system, which was then applied to verify commercial bank's current accounts and select the high suspicious ones.The experimental results show that the risk recognition accuracy rate of the intelligent strategy is much higher than the traditional one and reaches up to 85% above, which significantly promotes the efficiency of the accounting risk verification.

Key words: accounting risk event management, financial knowledge graph, anti-fraud, connected transaction

中图分类号: 

No Suggested Reading articles found!