arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 1908.07190cs.LGcs.CYstat.ML
收藏

业务流程服务中的合规性更改跟踪

Compliance Change Tracking in Business Process Services

IBM Research India(IBM印度研究院)

Srikanth G Tamilselvam, Ankush Gupta, Arvind Agarwal

摘要:

法规遵从性是指组织遵守与其业务相关的法律、法规、指南和规范。负责保持合规性的合规官不断努力跟上监管要求的大量变化。跟上变化需要两个主要任务:获取实际包含感兴趣的变化的监管公告,并将这些变化纳入业务流程。在本文中,我们专注于第一个任务,并提出了一个合规性变化跟踪系统,收集监管公告从政府网站,新闻网站,电子邮件订阅,分类的重要性,即通过一个层次分类器的可扩展性,和业务流程的适用性,通过多类分类器。对于这些分类器,我们用几种方法进行了实验,例如香草分类方法(例如朴素贝叶斯,逻辑回归等),分层分类方法,基于规则的方法,与各种预处理和特征选择方法的混合方法;并表明,尽管其他模型的丰富性,一个简单的分层分类与袋的字功能的工作最好的可扩展性分类器和多类逻辑回归的工作最好的适用性分类器。该系统已在全球交付中心部署,并收到了工资合规干事的积极反馈。

英文摘要:

Regulatory compliance is an organization's adherence to laws, regulations, guidelines and specifications relevant to its business. Compliance officers responsible for maintaining adherence constantly struggle to keep up with the large amount of changes in regulatory requirements. Keeping up with the changes entail two main tasks: fetching the regulatory announcements that actually contain changes of interest, and incorporating those changes in the business process. In this paper we focus on the first task, and present a Compliance Change Tracking System, that gathers regulatory announcements from government sites, news sites, email subscriptions; classifies their importance i.e Actionability through a hierarchical classifier, and business process applicability through a multi-class classifier. For these classifiers, we experiment with several approaches such as vanilla classification methods (e.g. Naive Bayes, logistic regression etc.), hierarchical classification methods, rule based approach, hybrid approach with various preprocessing and feature selection methods; and show that despite the richness of other models, a simple hierarchical classification with bag-of-words features works the best for Actionability classifier and multi-class logistic regression works the best for Applicability classifier. The system has been deployed in global delivery centers, and has received positive feedback from payroll compliance officers.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑