arXiv:2610.07006v1 Announce Type: new Abstract: Learning effective representations helps characterize the structure and dynamics of equity markets from financial data with a low signal-to-noise ratio...
The paper introduces Future‑Aligned Soft Contrastive Learning (FASCL), a representation learning framework that uses pairwise future return correlations as continuous supervision to improve asset retrieval. FASCL’s soft contrastive loss aligns retrieved assets with correlated future returns, and the authors propose a new evaluation protocol to directly assess future trajectory similarity. Experiments on 5,631 US‑listed securities outperform 14 baselines in future return correlation, rank information coefficient, trend consistency, and gross Sharpe ratio across various retrieval depths and basket sizes.
arXiv:2606. 29347v1 Announce Type: cross Abstract: Adaptive Financial Transformer (AFT) is proposed for stock return prediction under non-stationary financial markets.
arXiv:2609.04239v2 Announce Type: replace Abstract: This technical report presents EXAONE Forecast for Finance (EXAONE Finance), a financial time series foundation model (TSFM) tailored to financial...
arXiv:2508. 19006v2 Announce Type: replace-cross Abstract: This study investigates the pre-trained RNN attention models with the mainstream attention mechanisms, such as additive attention, Luong's three attentions, global self-attention and sliding window sparse attention, for the empirical asset pricing research on the top 420 large-cap US stocks.
The paper introduces a regime‑diagnosis framework for industrial time‑series forecasting, highlighting that canonical loss functions embed fixed statistical priors that are violated in real‑world demand regimes such as zero‑inflation, skewness, and high variability. It proposes the Regime‑wise Relative Bias Vector (RBV) as a metric‑agnostic diagnostic that decomposes bias into an intrinsic floor and an excess attributable to training. A large‑scale study across 13 loss objectives and 60,000+ series demonstrates that regime‑aware diagnosis distinguishes optimization‑from‑bias failures and that regime‑aware training can eliminate pooling‑induced bias that mere capacity scaling cannot.
arXiv:2606. 04576v1 Announce Type: cross Abstract: Learning Value-at-Risk (VaR) and Expected Shortfall (ES) is important for managing financial risks effectively.
arXiv:2607. 02344v1 Announce Type: cross Abstract: Transformer architectures have shown strong potential in time series forecasting, where multi-head self-attention is widely used to capture temporal dependencies across historical timestamps.
DIVINE is a cross‑market pretraining framework for financial time‑series that reconstructs 77 targets derived from 16 standard technical indicators using raw OHLCV data. Trained jointly on six equity markets, its lightweight 0.05M‑parameter encoder outperforms larger pretraining baselines and matches or exceeds larger financial foundation models in downstream stock ranking tasks. The study demonstrates that diverse indicator supervision and cross‑market training yield complementary gains, highlighting that supervision design and market diversity, rather than model size, drive strong transferable financial representations.
EXAONE Forecast for Finance (EXAONE Finance) is a financial time‑series foundation model designed to overcome the limitations of existing models that rely on self‑attention and assume fully observed data. It replaces self‑attention with a causal 1D convolution for temporal mixing and a group‑aware pooling MLP for variate mixing, achieving linear‑time complexity. The model is pretrained on a large, diverse financial corpus and, through masked context augmentation, learns to handle missing data, ultimately topping the FinVerse benchmark across accuracy, ranking, and profitability metrics.
arXiv:2607. 19385v1 Announce Type: new Abstract: This paper tackles the problem of stock ranking and portfolio construction under realistic investment settings by jointly modeling temporal dynamics and cross-sectional dependencies.
arXiv:2608. 14021v1 Announce Type: new Abstract: Transformer-based sequential recommenders with causal self-attention often rely heavily on the most recent interaction at inference time, but how this behavior is structurally expressed in the representation used for prediction remains unclear.