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 2304.03368cs.LGcs.HC
收藏

从解释到行动:一个端到端的异常推理与管理人在回路框架

From Explanation to Action: An End-to-End Human-in-the-loop Framework for Anomaly Reasoning and Management

Carnegie Mellon University(卡内基梅隆大学);Capital One(第一资本金融公司)

Xueying Ding, Nikita Seleznev, Senthil Kumar, C. Bayan Bruss, Leman Akoglu

AI总结:

本文提出ALARM端到端人在回路框架,支持从无监督异常检测、解释到通过设计新规则采取行动的完整挖掘周期,弥补了自主检测在现实高风险场景中难以落地的不足。

摘要:

异常通常是制造、医疗、金融和监控等各种系统中故障或低效的指标。尽管由于这种实际相关性,文献中存在大量有效的检测算法,但自主异常检测在现实场景中很少被使用。特别是在高风险应用中,检测之外的流程(如验证和故障排查)通常涉及人在回路。在这项工作中,我们引入了ALARM(Analyst-in-the-Loop Anomaly Reasoning and Management);这是一个端到端的框架,全面支持从检测到行动的异常挖掘周期。除了对新兴异常进行无监督检测外,它还提供异常解释和用于人在回路流程的交互式GUI——可视化探索、意义构建,以及最终通过设计新的检测规则来采取行动——这有助于闭合“回路”,因为新规则补充了基于规则的监督检测,而这是实践中许多已部署系统的典型特征。我们通过一系列与金融行业欺诈分析师的案例研究展示了该方法的有效性。

英文摘要:

Anomalies are often indicators of malfunction or inefficiency in various systems such as manufacturing, healthcare, finance, surveillance, to name a few. While the literature is abundant in effective detection algorithms due to this practical relevance, autonomous anomaly detection is rarely used in real-world scenarios. Especially in high-stakes applications, a human-in-the-loop is often involved in processes beyond detection such as verification and troubleshooting. In this work, we introduce ALARM (for Analyst-in-the-Loop Anomaly Reasoning and Management); an end-to-end framework that supports the anomaly mining cycle comprehensively, from detection to action. Besides unsupervised detection of emerging anomalies, it offers anomaly explanations and an interactive GUI for human-in-the-loop processes -- visual exploration, sense-making, and ultimately action-taking via designing new detection rules -- that help close ``the loop'' as the new rules complement rule-based supervised detection, typical of many deployed systems in practice. We demonstrate \method's efficacy through a series of case studies with fraud analysts from the financial industry.

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。

↑