# DIVINE: Simple Cross-Market Stock Pretraining via Diverse Indicator Reconstruction

arXiv: https://arxiv.org/abs/2610.02866 · HTML: https://mlsanity.com/paper/2610.02866/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 16 of its 37 references that are in the map.
- First posted on arXiv 2 Oct 2026.

## Builds on (most cited first, 16 of 16)

- [Masked Autoencoders Are Scalable Vision Learners](https://mlsanity.com/paper/2111.06377/) (2021)
- [A Time Series is Worth 64 Words: Long-term Forecasting with Transformers](https://mlsanity.com/paper/2211.14730/) (2022)
- [TS2Vec: Towards Universal Representation of Time Series](https://mlsanity.com/paper/2106.10466/) (2021)
- [Temporal Relational Ranking for Stock Prediction](https://mlsanity.com/paper/1809.09441/) (2018)
- [Qlib: An AI-oriented Quantitative Investment Platform](https://mlsanity.com/paper/2009.11189/) (2020)
- [TimesURL: Self-supervised Contrastive Learning for Universal Time Series Representation Learning](https://mlsanity.com/paper/2312.15709/) (2023)
- [MASTER: Market-Guided Stock Transformer for Stock Price Forecasting](https://mlsanity.com/paper/2312.15235/) (2023)
- [Kronos: A Foundation Model for the Language of Financial Markets](https://mlsanity.com/paper/2508.02739/) (2025)
- [FinCast: A Foundation Model for Financial Time-Series Forecasting](https://mlsanity.com/paper/2508.19609/) (2025)
- [Pre-training Time Series Models with Stock Data Customization](https://mlsanity.com/paper/2506.16746/) (2025)
- [DELPHYNE: A Pre-Trained Model for General and Financial Time Series](https://mlsanity.com/paper/2506.06288/) (2025)
- [Alpha Discovery Neural Network based on Prior Knowledge](https://mlsanity.com/paper/1912.11761/) (2019)
- [Deep Learning Based Residuals in Non-linear Factor Models: Precision Matrix Estimation of Returns with Low Signal-to-Noise Ratio](https://mlsanity.com/paper/2209.04512/) (2022)
- [Neural Network-based Automatic Factor Construction](https://mlsanity.com/paper/2008.06225/) (2020)
- [Cross-Sectional Asset Retrieval via Future-Aligned Soft Contrastive Learning](https://mlsanity.com/paper/2602.10711/) (2026)
- [Integrating Inductive Biases in Transformers via Distillation for Financial Time Series Forecasting](https://mlsanity.com/paper/2603.16985/) (2026)

## Abstract (arXiv)

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.