在不确定负载下实现金融预测的准时交付，保障决策时效性。
TIP-Search: Time-Predictable Inference Scheduling for Market Prediction under Uncertain Load
- 基于延迟分位数筛选可用模型，动态调度有限计算资源。
- 在TLOB FI-2010数据集上，准时准确率提升至0.239，截止时间满足率达0.962。
- 适合高实时性金融系统，尤其应对负载波动场景下的推理调度优化。
实时市场预测服务要求预测结果在决策截止前完成；延迟的正确预测无法使用。本文研究在不确定负载下，针对固定市场预测器的时间可预测推理调度问题。TIP-Search通过过滤符合延迟分位数的可行模型，在有限工作者间进行调度，并采用受保护的约束在线专家机制，在精度、队列压力与截止风险之间权衡。在优化部署池中，TIP-Search实现0.994原始准确率和0.991准时准确率。在官方TLOB FI-2010 h=10基准上，TIP-Search++将准时准确率从0.156提升至0.239，截止时间满足率从0.391提升至0.962。在匹配的h10性能回放系统中，OCO-ACPO实现0.303准时准确率和0.951截止时间满足率，相比RAMSIS/SneakPeek/utility类方法，准时准确率提升+0.00285（p=0.0118），截止时间满足率提升+0.0146（p=1.5×10⁻⁵）。SA-OCO-ACPO在非平稳压力下相较CPO提升0.188–0.417的准时/截止服务质量。该成果为系统调度结果，非广义订单簿分类器排行榜。
原文摘要 · Abstract (English)
Real-time market prediction services need correct predictions before a decision deadline; a correct prediction delivered late is not usable. TIP-Search studies time-predictable inference scheduling over fixed market predictors under uncertain load. It filters conformal latency-quantile feasible models, dispatches over finite workers, and uses shielded constrained online experts to trade accuracy, queue pressure, and deadline risk. On the optimized deployable pool, TIP-Search reaches 0.994 raw accuracy and 0.991 timely accuracy. On official TLOB FI-2010 h=10, TIP-Search++ raises timely accuracy from 0.156 to 0.239 and deadline satisfaction from 0.391 to 0.962. In matched h10 profiled systems replay, OCO-ACPO reaches 0.303 timely accuracy and 0.951 deadline satisfaction, with paired gains over RAMSIS/SneakPeek/utility-style comparators of $+0.00285$ timely accuracy ($p=0.0118$) and $+0.0146$ deadline satisfaction ($p=1.5{\times}10^{-5}$). SA-OCO-ACPO improves timely/deadline service by 0.188--0.417 over CPO under nonstationary stress. The claim is a systems scheduling result, not a broad LOB classifier leaderboard.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。