研究人员开发了一种名为非对称峰值感知损失（APAL）的新损失函数，旨在改进时间序列预测，特别是在欠预测风险高于过预测的应用中。APAL通过更严厉地惩罚欠预测并将训练重点放在峰值预测区域来解决MSE和MAE等标准对称目标函数的局限性。所提出的方法还包括一个新的评估协议，以更好地评估峰值关键预测性能，用尾部误差和峰值特定度量来补充传统度量。 AI
影响 这种新的损失函数可能在关键运营场景中带来更可靠的AI驱动预测，例如资源分配的需求预测。
排序理由 该集群包含一篇详细介绍时间序列预测新方法的论文。
AI 生成摘要 · Google Gemini · 来自 2 个来源。 我们如何撰写摘要 →
完整方法见我们的编辑标准。
arXiv:2607.14871v1 Announce Type: cross Abstract: In many operational time-series forecasting applications, such as crowd demand forecasting, the risk related to under-prediction is substantially higher than that of over-prediction. Accurate prediction of rare demand spikes plays…
In many operational time-series forecasting applications, such as crowd demand forecasting, the risk related to under-prediction is substantially higher than that of over-prediction. Accurate prediction of rare demand spikes plays a critical role in downstream tasks. Yet most tim…