Application and practice of machine learning model in real-time anti-fraud in the era of digital finance

Hanping CAO; Xiaojing ZHANG; Ruijie ZHU; Xiaola HUANG

doi:10.11959/j.issn.2096-6652.201939

您当前的位置：

首页 >

文章列表页 >

Application and practice of machine learning model in real-time anti-fraud in the era of digital finance

Regular Papers | 更新时间：2024-06-05

- Application and practice of machine learning model in real-time anti-fraud in the era of digital finance
- Chinese Journal of Intelligent Science and Technology Vol. 1, Issue 4, Pages: 342-351(2019)
- 作者机构：
- 作者简介：
- 基金信息：
- DOI：10.11959/j.issn.2096-6652.201939
  CLC： TP391
- Published Online：2019-12，
  
  Published：20 December 2019
- 稿件说明：
移动端阅览
Hanping CAO, Xiaojing ZHANG, Ruijie ZHU, et al. Application and practice of machine learning model in real-time anti-fraud in the era of digital finance[J]. Chinese journal of intelligent science and technology, 2019, 1(4): 342-351.
DOI：

Hanping CAO, Xiaojing ZHANG, Ruijie ZHU, et al. Application and practice of machine learning model in real-time anti-fraud in the era of digital finance[J]. Chinese journal of intelligent science and technology, 2019, 1(4): 342-351. DOI： 10.11959/j.issn.2096-6652.201939.

摘要

近年来，数字金融蓬勃发展，金融科技日趋成熟，信息技术的发展对社会产生巨大积极作用的同时也带来了新型风险，网络黑产呈爆发式增长，电信网络诈骗给人民群众造成了巨大的财产损失。在数字金融时代，商业银行既迎来了新的机遇与动力，又面临着新的挑战和数字化变革的要求，线上金融业务已经成为新的主战场。在此背景下，基于 RFM 高维衍生特征和对机器学习算法的研究，构建了基于高维交易行为画像的事中反欺诈机器学习模型。依托大数据、流计算等技术，通过在系统化部署、应用策略以及模型迭代优化等环节的实践，形成了一套基于机器学习模型的事中风控方案。实践证实，该模型的AUC达到了0.972，可以敏锐洞察欺诈风险，实现毫秒级的欺诈交易识别，对于提升线上数字金融业务的事中风控能力具有一定的推广价值和借鉴意义。

Abstract

In recent years

with the rapid development of FinTech

digital finance has flourished and brought huge positive effect on society.Meanwhile

new risks have been introduced into banks.For example

the black production related to network security has experienced explosive growth

and telecommunication network fraud has caused property losses to the public.In the era of digital finance

the commercial banks have not only ushered in new opportunities and dynamics

but also faced new challenges and requirements for digital transformation.As a result

e-finance has become a new battlefield.With this context

a real-time anti-fraud machine learning model based on high-dimensional transaction behavior portrait through enhanced RFM feature-derivation and machine learning modeling was established in this paper.Relying on the new technologies such as big data

stream computing

a model application solution to real-time risk control was formed including systematic deployment

model application strategies and iterative model optimization.Through practical observation

the AUC of the model reaches 0.972

which provides a keen insight into fraud risk

realizes millisecond-level risk identification

and promotes risk control ability of e-finance significantly.

关键词

Keywords

references

中国人民银行 . 金融科技（FinTech）发展规划（2019-2021年） [R ] . 2019 .

Bank of China . Development plan of FinTech(2019-2021) [R ] . 2019 .

张旭 , 赵奕 . “在线实时决策＋离线机器学习”实现高效实时反欺诈 [J ] . 金融电子化 , 2016 ( 12 ):89.

ZHANG X , ZHAO Y . “Online real-time decision-making + offline machine learning” for efficient real-time anti-fraud [J ] . Financial Computerizing , 2016 ( 12 ):89.

FRIEDMAN J H . Greedy function approximation:a gradient boosting machine [J ] . The Annals of Statistics , 2001 , 29 ( 5 ): 1189 - 1232 .

CHEN T Q , GUESTRIN C . XGB：a scalable tree boosting system [C ] // The 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining,August 13- 17,2016,San Francisco,USA . New York:ACM Press , 2016 : 785 - 794 .

刘彧祺 , 张智斌 , 陈昊昱 , 等 . 基于XGBoost 集成的可解释信用评分模型 [J ] . 数据通信 , 2019 ( 3 ): 27 - 32 .

LIU Y Q , ZHANG Z B , CHEN H Y , et al . Interpretable credit scoring model based on XGBoost integration [J ] . Shuju Tongxin , 2019 ( 3 ): 27 - 32 .

成晨 , 程新洲 , 张恒 , 等 . 智能化调参的XGBoost 算法及其在电信营销中的应用 [J ] . 邮电设计技术 , 2018 , 512 ( 10 ): 26 - 30 .

CHENG C , CHENG X Z , ZHANG H , et al . Intelligent parameter adjustment XGBoost and its application in telecom marketing [J ] . Designing Techniques of Posts and Telecommunications , 2018 , 512 ( 10 ): 26 - 30 .

仵伟强 , 后其林 . 基于机器学习模型的消费金融反欺诈模型与方法 [J ] . 现代管理科学 , 2018 ( 10 ): 51 - 54 .

WU W Q , HOU Q L . Anti-fraud models and methods for consumer finance based on machine learning models [J ] . Modern Management Science , 2018 ( 10 ): 51 - 54 .

Views

268

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

Analysis and prediction of GitHub company influence based on machine learning

Sidelink resource allocation algorithm of C-V2X based on deep Q learning

Theoretical framework of brain modelling and highlighted problems

A survey on evolutionary ensemble learning algorithm

Related Author

Mingyu WANG

Qingyuan GONG

Jingjing QU

Xin WANG

Hui XU

Dongwei HU

Xiaolu FENG

Yi HU

Related Institution

School of Computer Science, Fudan University

Research Institute of Intelligent Complex Systems, Fudan University

Shanghai Artificial Intelligent Laboratory

The 54th Institute of China Electronics Technology Group Corporation

The Shiyan School Attached to Shijiazhuang No.2 Middle School

Postal code：100079
Tel：（010）53879206 Email：cjist@bjxintong.com.cn
Technical support is provided by Beijing Founder electronics co., LTD 京ICP备09064830号-19 京公网安备11010802024621
It is recommended to read the content of this site in Chrome&IE9+. Please switch to extreme mode in browser 360.
Cookies We use cookies to help provide and enhance our service and tailor content. By continuing, you agree to the use of cookies.
Total Visits：35685 Visits Today：160

⁰