基于金融知识图谱的会计欺诈风险识别方法

doi:10.11959/j.issn.2096-0271.2021029

Abstract

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

CLC Number:

TP311，F832

Qiang CHEN, Shiya DAI. Recognition method of accounting fraud risk based on financial knowledge graph[J]. Big Data Research, 2021, 7(3): 116-129.

Figures/Tables 21

References 18

[1]	吴建光 . 金融科技与会计管理数字化转型[J]. 金融会计, 2020(1): 36-38.
	WU J G . Financial technology and digital transformation of accounting management[J]. Financial Accounting, 2020(1): 36-38.
[2]	刘瑞霞 . 打造基于大数据的智能化风控体系[J]. 金融电子化, 2018(8): 57-58.
	LIU R X . Configuration of intelligent risk management system based on big data[J]. Financial Computerizing, 2018(8): 57-58.
[3]	姜增明, 陈剑锋, 张超 . 金融科技赋能商业银行风险管理转型[J]. 当代经济管理, 2019,41(1): 85-90.
	JIANG Z M , CHEN J F , ZHANG C . The empowerment of financial technology on the risk management transformation of commercial banks[J]. Contemporary Economy＆ Management, 2019,41(1): 85-90.
[4]	柴洪峰, 王帅, 涂晓军 ,等. 智能化金融科技创新监管工具:理念、平台框架和展望[J]. 智能科学与技术学报, 2020,2(3): 214-226.
	CHAI H F , WANG S , TU X J ,et al. Intelligent innovative regulatory tools on financial technology:concept,platform framework,and prospects[J]. Chinese Journal of Intelligent Science and Technology, 2020,2(3): 214-226.
[5]	陶睿, 吴继春, 谢胜强 ,等. 深度学习和知识图谱在智能监管中的应用研究[J]. 金融纵横, 2019(8): 56-66.
	TAO R , WU J C , XIE S Q ,et al. Applied research on deep learning and knowledge graph in intelligent regulation[J]. Financial Perspectives Journal, 2019(8): 56-66.
[6]	陶士贵, 相瑞 . 基于大数据技术的商业银行反洗钱风险识别“穿透”研究[J]. 金融发展研究, 2020(7): 73-78.
	TAO S G , XIANG R . Research on penetration of anti-money laundering risk identification of commercial banks based on big data technology[J]. Journal of Financial Development Research, 2020(7): 73-78.
[7]	金磐石, 万光明, 沈丽忠 . 基于知识图谱的小微企业贷款申请反欺诈方案[J]. 大数据, 2019,5(4): 100-112.
	JIN P S , WAN G M , SHEN L Z . Knowledge graph-based fraud detection for small and micro enterprise loans[J]. Big Data Research, 2019,5(4): 100-112.
[8]	王成, 舒鹏飞 . WEB:一种基于网络嵌入的互联网借贷欺诈预测方法[J]. 大数据, 2019,5(6): 85-100.
	WANG C , SHU P F . WEB:a fraud prediction method of Internet lending using network embedding[J]. Big Data Research, 2019,5(6): 85-100.
[9]	凡友荣, 杨涛, 孔华锋 ,等. 基于知识图谱的电信欺诈通联特征挖掘方法[J]. 计算机应用与软件, 2019,36(11): 182-187.
	FAN Y R , YANG T , KONG H F ,et al. Calling features mining method of telecom fraud based on knowledge graph[J]. Computer Applications and Software, 2019,36(11): 182-187.
[10]	魏瑾, 李伟华, 潘炜 . 基于知识图谱的智能决策支持技术及应用研究[J]. 计算机技术与发展, 2020,30(1): 1-6.
	WEI J , LI W H , PAN W . Research on intelligent decision support technology and application based on knowledge graph[J]. Computer Technology and Development, 2020,30(1): 1-6.
[11]	陈成, 陈跃国, 刘宸 ,等. 意图知识图谱的构建与应用[J]. 大数据, 2020,6(2): 57-68.
	CHEN C , CHEN Y G , LIU C ,et al. Constructing and analyzing intention knowledge graphs[J]. Big Data Research, 2020,6(2): 57-68.
[12]	王昊奋, 丁军, 胡芳槐 ,等. 大规模企业级知识图谱实践综述[J]. 计算机工程, 2020,46(7): 1-13.
	WANG H F , DING J , HU F H ,et al. Survey on large scale enterprise-level knowledge graph practices[J]. Computer Engineering, 2020,46(7): 1-13.
[13]	胡扬, 闫宏飞, 陈翀 . 面向金融知识图谱的实体和关系联合抽取算法[J]. 重庆理工大学学报(自然科学), 2020,34(5): 139-149.
	HU Y , YAN H F , CHEN C . Joint entity and relation extraction for constructing financial knowledge graph[J]. Journal of Chongqing University of Technology(Natural Science), 2020,34(5): 139-149.
[14]	李任之, 李博杰, 张国桢 ,等. 基于CouchDB和Elastic Search的高性能化学结构搜索引擎与数据库的构建[J]. 化学物理学报, 2018,31(3): 341-349.
	LI R Z , LI B J , ZHANG G Z ,et al. A highperformance and flexible chemical structure＆ data search engine built on CouchDB ＆Elastic Search[J]. Chinese Journal of Chemical Physics, 2018,31(3): 341-349.
[15]	吴金全 . 有向图的强连通分量及应用[J]. 软件, 2014,35(3): 72-75.
	WU J Q . The SCC of digraph and application[J]. Computer Engineering ＆Software, 2014,35(3): 72-75.
[16]	吕华揆, 洪亮, 马费成 . 金融股权知识图谱构建与应用[J]. 数据分析与知识发现, 2020,4(5): 27-37.
	LYU H K , HONG L , MA F C . Constructing knowledge graph for financial equities[J]. Data Analysis and Knowledge Discovery, 2020,4(5): 27-37.
[17]	吴结凤, 黄学进, 李晋川 ,等. 脉动流模拟系统血压波形相似度算法研究[J]. 医用生物力学, 2020,27(5): 515-520.
	WU J F , HUANG X J , LI J C ,et al. Similarity measurement of blood pressure waveforms for pulsatile flow simulation system[J]. Journal of Medical Biomechanics, 2020,27(5): 515-520.
[18]	藏根林, 王亚强, 吴庆蓉 ,等. 知识图谱中的关系方向与强度研究[J]. 大数据, 2019,5(3): 96-103.
	ZANG G L , WANG Y Q , WU Q R ,et al. Study on direction and strength of relation based on knowledge graph[J]. Big Data Research, 2019,5(3): 96-103.

Metrics

Recommended 0

No Suggested Reading articles found!

规则逻辑描述	提取指标	指标化规则配置
本行对公活期存款账户发生借方出账金额达单笔≥800万元，且交易走款未验印或验印手工通过	主账户类型	主账户类型=“对公定期”
	借贷标志	且：借贷标志=“借方”
	交易金额	且：交易金额≥“800万元”
	验印结果	且：验印结果 =“未验印”or“手工通过”

方法		识别目标
图计算	资金交易闭环分析	资金回流到初始账户的闭环交易
	账户关联强度分析	非直接交易账户之间的隐藏交易关系
知识推理	账户分层穿透匹配	资金通过中间账户进入限制用途账户
	资金转移模式匹配	大额资金的归集与分散，如非法集资、洗钱等

指标类别	指标名称	指标含义
客户类	对账地址	企业在银行对公账户对账单上填写的地址
	联系电话	企业在银行开立账户的联系电话
	是否开启通知	企业是否开启银行短信、精灵信使等通知
交易类	主账户类型	发生交易的企业账户主账户类型
	借贷标志	账户交易的资金转移方向
	交易账户类型	主账户发生交易的对手账户类型
运营类	账户验印结果	企业提交材料上的印章与开户时的预留印章是否一致
	对账是否成功	交易账目核对是否一致
机构类	近3月账户开立数	营业机构近3个月内开立的对公账户数量
	近1月借方累计金额	营业机构近1个月内所有对公主账户发生借方交易的总金额

实体	关系类型		关系表示
账户实体	交易关系	“账户”__(交易)__“账户”
非账户实体（证件、手机号、设备IP、经营机构等）	非交易关系	“账户”__(拥有)__“证件”
		“账户”__(联系方式)__“手机号”
		“账户”__(使用)__“设备IP”
		“账户”__(开户)__“经营机构”

类别	浅层关联特征
图谱类	多个账户的联系人电话相同
图谱类	账户在多个设备登录
图谱类	不同客户对账信息中共享同一个对账IP
图谱类	经营机构存在多个异常账户

Recognition method of accounting fraud risk based on financial knowledge graph

RichHTML

PDF下载

Knowledge

Abstract

Cite this article

share this article

Figures/Tables 21

References 18

Related Articles 3

Metrics

Recommended 0

类别	深层关联特征
图谱类	资金通过内部账户转向非同名账户
图谱类	账户转出资金高度集中于某一个账户
图谱类	指定购买理财资金转入其他类型账户
图谱类	贷款资金经多层周转后用于禁止性领域
图谱类	多对一账户归集
图谱类	与异常账户关联强度较高
图谱类	资金以固定时间间隔转出相同金额
图谱类	大额资金经多条路径转入关联方账户

实验组	样本数/个	应用策略	预警数/个	确认数/个	确认率
策略1	1 500万	账户基础特征规则	2.1万	4 230	20.1%
策略2	1 400万	账户基础特征规则+账户关联特征规则	4 067	2 621	64.4%

[1]	Cheng WANG, Pengfei SHU. WEB:a fraud prediction method of Internet lending using network embedding [J]. Big Data Research, 2019, 5(6): 85-100.
[2]	Panshi JIN,Guangming WAN,Lizhong SHEN. Knowledge graph-based fraud detection for small and micro enterprise loans [J]. Big Data Research, 2019, 5(4): 100-112.
[3]	Pengfei HU. Application of FinTech in internet financial industry risk prevention [J]. Big Data Research, 2018, 4(1): 117-123.