arXiv：cs.LG（机器学习，全量分类）· Shivam Gupta·· 14 小时前AI 评分33
金融 AI 的应急暴露路由：中断风险与不可分割决策的代价
Contingent Exposure Routing for Financial AI: Outage Risk and the Cost of Indivisible Decisions
AI 导读
研究提出基于局部市场冲击响应矩阵的中断应急路由框架，用于分析模型故障切换后金融机构间决策误差的共享变化。在 60 个合成投资组合网络、11,340 次场景评估中，交换程序在单端点和双端点移除下分别降低风险 6.57% 和 10.53%；对 1,024 条真实 API 响应的回放仅带来 3.30% 的留出集降幅。强相关误差、劣质端点和不可分割性都会限制分散化效果。
正文
Abstract:Model failover restores availability, but changes which financial institutions share decision errors. We formulate outage-contingent routing through a local market-impact response matrix and study expected squared price displacement. A symmetric construction shows that a shared backup can leave an order-one concentration floor as the number of primary endpoints grows, while balanced fallback risk decreases inversely with the surviving endpoint count. For indivisible decisions, we derive the exact second moment of independent randomized routing and an effective-exposure granularity that determines its gap from fractional allocation. Conditional-expectation rounding gives a finite-agent bound without coupled quotas; a separate swap procedure preserves endpoint counts and is assessed against dual lower bounds. Across 60 synthetic portfolio networks and 11,340 scenario evaluations, the latter reduces risk by 6.57% and 10.53% for single and double endpoint removals at the central feedback setting with independent errors. A replay of 1,024 recorded API responses on constructed rebalancing tasks gives a smaller held-out reduction of 3.30% (paired bootstrap interval 2.07--4.57%). Strongly aligned errors, inferior endpoints, and indivisibility limit diversification. The contribution is an auditable routing stress test and implementation analysis, not an estimate of real-market crash probabilities.
| Comments: | 15 pages, 6 figures, 3 tables. Code and data: this https URL |
| Subjects: | Machine Learning (cs.LG) |
| Cite as: | arXiv:2610.00239 [cs.LG] |
| (or arXiv:2610.00239v1 [cs.LG] for this version) | |
| https://doi.org/10.48550/arXiv.2610.00239 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Shivam Gupta [view email]
[v1]
Wed, 23 Sep 2026 06:56:27 UTC (108 KB)
来源：arXiv：cs.LG（机器学习，全量分类） · arxiv.org