arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1806.07129cs.LGcs.AIstat.ML
收藏

用于欺诈检测的实例级推理:一个案例研究

Instance-Level Explanations for Fraud Detection: A Case Study

Eindhoven University of Technology(埃因霍温理工大学);Achmea BV(Achmea公司)

Dennis Collaris, Leo M. Vink, Jarke J. van Wijk

摘要:

欺诈检测是一个困难的问题,可以从预测建模中受益。然而,预测的验证是具有挑战性的;对于单个保单,模型仅提供预测分数。我们提出了一个案例研究,我们反映了不同的实例级模型解释技术,以帮助欺诈检测团队在他们的工作。为此,我们设计了两个新颖的仪表板,结合了各种最先进的解释技术。这些使领域专家能够分析和理解预测,大大加快了过滤潜在欺诈案件的过程。最后,我们讨论了经验教训,并概述了开放的研究问题。

英文摘要:

Fraud detection is a difficult problem that can benefit from predictive modeling. However, the verification of a prediction is challenging; for a single insurance policy, the model only provides a prediction score. We present a case study where we reflect on different instance-level model explanation techniques to aid a fraud detection team in their work. To this end, we designed two novel dashboards combining various state-of-the-art explanation techniques. These enable the domain expert to analyze and understand predictions, dramatically speeding up the process of filtering potential fraud cases. Finally, we discuss the lessons learned and outline open research issues.

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。

↑