发表机构
Data Science Research Centre; Tampere University（数据科学研究中心; 坦佩雷大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
本文提出UQ-LOB，一种轻量级、编码器无关的不确定性量化模块，用于限价订单簿中间价预测，通过上下文集和校准分布提供置信度，并在52亿LOB事件上显著提升选择性预测的F1分数。
AI 中文摘要
从限价订单簿（LOB）数据预测短时间尺度的中间价变动是算法交易的核心，然而大多数深度LOB预测器是点预测器：它们输出方向或位移，但从不表明哪些预测可以被信任。我们引入了UQ-LOB，一个轻量级、编码器无关的不确定性量化模块，可附加到任何预训练的LOB编码器上，并本着注意力神经过程的精神，使每个预测以一组最近完成的、结果已实现窗口的上下文集为条件。UQ-回归变体输出未来tick位移的校准高斯分布，而UQ-分类变体输出下跌/上涨/平稳的类别分布。两者都暴露了一个标量置信度（预测的信噪比或类别概率），支持选择性预测。在跨越七个加密货币资产和5、10、15秒时间尺度的52亿个LOB事件上，UQ-回归实现了接近名义上的68%区间覆盖率，并且将预测限制在最自信的10%上，在每个时间尺度上，UQ-回归的方向宏F1提高了0.11-0.15，UQ-分类提高了0.05-0.11。在大的、具有经济意义的变动中，最紧的置信度层级在5秒时间尺度上达到了方向F1为0.88（下跌）和0.83（上涨）。
英文摘要
Forecasting short-horizon mid-price movements from limit order book (LOB) data is central to algorithmic trading, yet most deep LOB forecasters are point predictors: they output a direction or a displacement, but never indicate which of their forecasts can be trusted. We introduce UQ-LOB, a lightweight, encoder-agnostic uncertainty quantification module that attaches to any pretrained LOB encoder and, in the spirit of attentive neural processes, conditions each forecast on a context set of recently completed windows whose outcomes are already realised. The UQ-regression variant outputs a calibrated Gaussian over the future tick displacement, while the UQ-classification variant outputs a categorical distribution over down/up/stationary. Both expose a scalar confidence (predicted signal-to-noise ratio or class probability) that supports selective prediction. On 5.2 billion LOB events across seven cryptocurrency assets and horizons of 5, 10 and 15 seconds, UQ-regression attains near-nominal 68% interval coverage, and restricting to the most confident 10% of predictions raises directional macro F1 by 0.11-0.15 for UQ-regression and 0.05-0.11 for UQ-classification, at every horizon. On large, economically meaningful moves, the tightest confidence tier reaches a directional F1 of 0.88 (down) and 0.83 (up) at the 5-second horizon.
