ISSN 1000-1239 CN 11-1777/TP

计算机研究与发展 ›› 2020, Vol. 57 ›› Issue (8): 1755-1768.doi: 10.7544/issn1000-1239.2020.20200217

所属专题: 2020数据挖掘与知识发现专题

• 人工智能 • 上一篇    下一篇



  1. 1(中国科学技术大学计算机科学与技术学院 合肥 230027);2(新疆师范大学计算机科学技术学院 乌鲁木齐 830054);3(腾讯科技(北京)有限公司 北京 100080);4(天津大学管理经济学院 天津 300072) (
  • 出版日期: 2020-08-01
  • 基金资助: 
    国家自然科学基金项目( U1605251,61727809,61562087);新疆维吾尔自治区高校科研计划项目(XJEDU2016S068);新疆师范大学重点实验室课题(XJNUSYS102018B03)

A Hierarchical Attention Mechanism Framework for Internet Credit Evaluation

Chen Yanmin1,2, Wang Hao1, Ma Jianhui1, Du Dongfang3, Zhao Hongke4   

  1. 1(School of Computer Science and Technology, University of Science and Technology of China, Hefei 230027);2(School of Computer Science and Technology, Xinjiang Normal University, Urumqi 830054);3(Tencent Inc, Beijing 100080);4(College of Management and Economics, Tianjin University, Tianjin 300072)
  • Online: 2020-08-01
  • Supported by: 
    This work was supported by the National Natural Science Foundation of China (U1605251, 61727809, 61562087), the Scientific Program of the Higher Education Institution of Xinjiang (XJEDU2016S068), and the Xinjiang Normal University Key Laboratory Project (XJNUSYS102018B03).

摘要: 随着互联网的发展,基于用户信用的在线服务产品也越来越多地应用到各个领域.在这些信用数据中,除了传统的信贷数据,还包含用户网上消费数据等,因此如何利用这些数据来评估用户的信用等级是一个亟待解决的重要问题.之前的方法主要是基于信贷领域属性的研究,缺乏在互联网领域的研究,并且这些方法很少考虑用户的不同属性对其信用的不同的重要程度.因此,为了解决这些问题,提出一个基于层级注意力机制用户信用评估模型框架(HAM-UCE),模型首先构建用户信用画像,然后利用层级注意力机制在多个注意力层逐步获取更重要的用户属性特征,实现对用户信用等级的评估.实验结果表明该方法能够有效地实现对用户信用进行等级评估,能够比基准算法取得更好的性能.

关键词: 注意力机制, 层级神经网络, 用户信用评估, 信用等级, 特征提取

Abstract: With the development of the Internet, online service products based on user credit have been increasingly applied to various fields. The Internet user credit data, which contains diverse types of data, describes the user’s various aspects. Thus how to use user’s data to evaluate users’ credit ratings on the Internet is an important issue. Most of previous research methods mainly focus on the traditional credit evaluation which is based on the extraction of attributes in the credit field. However, there are only a few of work on Internet credit evaluation. And those work lies in lacking efficient methods to consider the different importance of multiple user attributes on their credit history. Therefore, to solve these problems, this paper presents a hierarchical attention mechanism framework for user credit evaluation based on users’ profiles. Specifically, first, the model builds user profile with user attributes such as user credit history and user behaviors to describe the coarse granularity of users. Then, the significance of user’s attribute with multiple attention layers is gradually obtained to achieve the evaluation of user credit ratings. Extensive experimental results on the public dataset have demonstrated that this model can achieve better performance on evaluation of user than other benchmark algorithms.

Key words: attention mechanism, hierarchical neural network, user credit evaluation, credit level, feature extraction