Researchers Propose New Framework for Optimizing Training Labels in Financial Forecasting Models
Researchers have identified what they call the 'Label Horizon Paradox,' finding that the optimal training signal for deep learning financial forecasting models often differs from the actual prediction target. The work challenges the standard assumption that training labels must directly mirror inference goals, showing that intermediate time horizons governed by market dynamics can yield better generalization. The finding opens a new line of inquiry into how supervision signals are designed for financial AI models.
A preprint posted to arXiv proposes that deep learning models used in financial forecasting are routinely trained with suboptimal supervision signals. The authors argue that the conventional practice of aligning training labels exactly with prediction targets — for example, using next-day returns to predict next-day returns — ignores a dynamic trade-off between signal realization and noise accumulation across different time horizons. They term this mismatch the 'Label Horizon Paradox,' grounding it theoretically in the competition between marginal signal and noise as the label horizon shifts. To address this, the team developed a bi-level optimization framework capable of autonomously identifying the best proxy label within a single training run, without requiring manual horizon search. Experiments conducted on large-scale financial datasets reportedly show consistent performance improvements over conventional baselines. The paper is currently a preprint and has not yet undergone formal peer review, though it has been revised four times since its initial submission in February 2026.
What's missing
The paper has not yet been peer-reviewed. Key limitations not detailed in the abstract include: which specific asset classes or markets were tested, whether improvements hold out-of-sample across different market regimes, the computational overhead of the bi-level optimization relative to standard training, and whether the optimal proxy label horizon is stable over time or shifts with changing market conditions.
What different sources said
- arXiv cs.LGCenter
The Label Horizon Paradox: Rethinking Supervision Targets in Financial Forecasting
Related
Gut Bacteria Enzyme Found to Break Down Heat-Processed Food Compounds, Producing Novel Biogenic Amines
Researchers have discovered that an enzyme in common gut bacteria can degrade N-epsilon-carboxymethyllysine (CML), a compound formed during thermal food processing, producing previously unknown biogenic amines. The enzyme, ornithine decarboxylase SpeC from enterobacteria, acts on CML and related modified lysine derivatives through a low-level 'underground' catalytic activity. This finding suggests a previously unrecognized communication axis between thermally processed dietary compounds and gut microbial physiology, with potential implications for host health.
Full-Length Gene Sequencing Reveals Two Distinct Bacterial Communities in Black-Legged Ticks Expanding Into Canada
Researchers used Oxford Nanopore full-length 16S rRNA gene sequencing to characterize the microbiome of Ixodes scapularis black-legged ticks collected in Nova Scotia, Canada, distinguishing between tick-adapted bacteria and environmentally acquired bacteria. The study comes as I. scapularis — the primary vector of Lyme disease — is rapidly expanding northward into Canada due to climate change. The findings suggest that environmentally derived bacteria in tick microbiomes are not mere contamination, which has implications for how tick microbiome data is collected and interpreted across surveillance studies.
Study Identifies Metabolic Link Between Cell Envelope Stress and Biofilm Formation in Bacteria
Researchers have discovered that the metabolite acetyl-CoA directly inhibits enzymes that degrade the bacterial signaling molecule c-di-GMP, connecting cell envelope biosynthesis stress to biofilm formation in Pseudomonas aeruginosa. The study found that sub-inhibitory concentrations of antibiotics targeting early peptidoglycan biosynthesis — but not other antibiotic classes — elevate c-di-GMP levels by reducing phosphodiesterase activity, with acetyl-CoA competing for the enzyme active site. Because the relevant enzyme domain is broadly conserved across bacterial species, this checkpoint mechanism may be widespread and could have implications for understanding antibiotic-induced biofilm responses.