计算机应用与软件2024，Vol.41Issue(5)：92-95,117,5.DOI:10.3969/j.issn.1000-386x.2024.05.014
一种基于图卷积神经网络的网络小贷反欺诈方案
AN ANTI-FRAUD SCHEME BASED ON GRAPH CONVOLUTIONAL NETWORK FOR NETWORK MICRO-FINANCE
毛巧儿 1刘晓强 2李柏岩 2蔡立志 3胡芸3
作者信息
- 1. 东华大学计算机科学与技术学院 上海 201620||上海市计算机软件评测重点实验室 上海 201112
- 2. 东华大学计算机科学与技术学院 上海 201620
- 3. 上海市计算机软件评测重点实验室 上海 201112
- 折叠
摘要
Abstract
Aiming at the phenomenon of network micro-finance gang fraud,this paper proposes an anti-fraud scheme based on graph convolutional network for network micro-finance.According to the knowledge of credit field,the knowledge graph was defined by the top-down method,and the user network was built by the user call logs.The data was preprocessed to obtain the features of fraud risk.The adjacency matrix and features of the relational network were used as the input of graph convolutional network,and the feature propagation of the second-order neighbors was aggregated to calculate the default probability of the unlabeled node.Experimental results show that compared with the DeepWalk model combined with logistic regression,XGBoost,GBDT classifier,the KS value of our method is improved by 0.214,0.168,0.076 respectively,which distinguishes between positive and negative samples better,and effectively identifies fraud gang.关键词
图神经网络/反欺诈/网络小贷/知识图谱Key words
Graph convolutional network/Anti-fraud/Network micro-finance/Knowledge graph分类
信息技术与安全科学引用本文复制引用
毛巧儿,刘晓强,李柏岩,蔡立志,胡芸..一种基于图卷积神经网络的网络小贷反欺诈方案[J].计算机应用与软件,2024,41(5):92-95,117,5.
