arXiv：cs.LG· Kuan-Yu Chen, Shu-Cheng Zheng, Yu-Chen Den, Wei-Cheng Liao, Tien-Hao Chang·· 3 小时前AI 评分33
DIVINE：通过多指标重建实现简单跨市场股票预训练
DIVINE: Simple Cross-Market Stock Pretraining via Diverse Indicator Reconstruction
AI 导读
DIVINE 是一种跨市场预训练框架，通过从原始 OHLCV 历史重建技术指标来学习股票表征，在六个股票市场数据集上联合预训练，重建 16 个标准指标衍生的 77 个目标。
正文
Abstract:Financial time-series pretraining typically learns from masked observations, contrastive relations, or future outcomes---yet existing objectives struggle to simultaneously avoid future-supervision uncertainty and maintain return-prediction alignment. We propose DIVINE (DIVerse INdicator rEconstruction), a simple cross-market pretraining framework that reconstructs technical indicators from raw OHLCV history. Computed from observed price-volume history, technical indicators provide consistently defined supervision across markets while summarizing diverse market dynamics with established relevance to return prediction. Pretrained jointly on six-equity market datasets, DIVINE reconstructs 77 targets derived from 16 standard indicators and transfers only the learned encoder to downstream stock ranking. Across all six markets, DIVINE achieves the strongest average portfolio performance with a lightweight 0.05M-parameter encoder, outperforming pretraining baselines and matching or exceeding substantially larger financial foundation models, while remaining robust and data-efficient. Systematic analyses show that indicator diversity and market diversity provide complementary gains in transfer. Together, these results suggest that supervision design and cross-market diversity---rather than model scale---are the key drivers of strong, transferable financial representations.
| Subjects: | Machine Learning (cs.LG); Computational Engineering, Finance, and Science (cs.CE) |
| Cite as: | arXiv:2610.02866 [cs.LG] |
| (or arXiv:2610.02866v1 [cs.LG] for this version) | |
| https://doi.org/10.48550/arXiv.2610.02866 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Kuan-Yu Chen [view email]
[v1]
Fri, 2 Oct 2026 06:04:56 UTC (456 KB)
来源：arXiv：cs.LG · arxiv.org