提出无需重训练的K线概率预测一致性修复方法
Crossing-Free Probabilistic K-Line Forecasts Without Retraining
- 通过顺序投影法实现无参数、无训练的预测校正
- 使所有测试数据的交叉率降至零，且保持预测精度
- 适用于任意模型生成的预测，特别适合基础模型
概率性K线预测需同时描述开盘价、最高价、最低价和收盘价的不确定性，但会引发分位数交叉和K线交叉问题。前者指高分位预测低于低分位预测，后者指最低价高于开盘或收盘，或最高价低于开盘或收盘。现有方法通常仅解决单一问题，依赖输出重排、特殊结构或惩罚项。本文提出无参数、无训练的K线-分位数顺序投影（KQSP）方法，可应用于任何模型生成的预测。相比其他修正方法，KQSP在保持预测准确性的同时，大幅减少对原始预测的修正幅度。为缓解模型偏差，我们使用多种模型（包括预训练基础模型）进行评估。实验表明，KQSP在所有测试数据上将分位数交叉和K线交叉率均降至零。结果证明：概率性K线一致性可独立于生成过程强制执行，无需重新训练。
原文摘要 · Abstract (English)
Probabilistic K-line forecasting describes uncertainty in four complementary prices, namely open--high--low--close (OHLC). However, it introduces two consistency problems: quantile crossing and K-line crossing. Quantile crossing occurs when a higher-quantile forecast falls below a lower-quantile forecast, while K-line crossing occurs when the forecast low exceeds the open or close, or the forecast high falls below the open or close. Existing solutions generally address only one problem through output reordering, specialized architectures, or penalized training objectives. We propose K-line--Quantile Sequential Projection (KQSP), a parameter-free and training-free reconciliation method applicable to forecasts produced by any model. Compared with other crossing solutions, KQSP preserves predictive accuracy while producing substantially smaller corrections to the original forecasts. To mitigate model bias, we evaluate KQSP using various models, including pretrained foundation models. KQSP reduces both quantile and K-line crossing rates to zero for all test data undertaken. These results show that probabilistic K-line consistency can be enforced independently of forecast generation and without retraining.
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。