Cross-Sectional Asset Retrieval via Future-Aligned Soft Contrastive Learning

2026-02-11

AI Summary

This work proposes FASCL, a novel asset retrieval framework designed to capture future return correlations—a challenge inadequately addressed by traditional methods that rely on historical prices or industry labels. FASCL introduces pairwise future return correlation as a continuous supervisory signal and incorporates soft contrastive learning to learn forward-looking representations. To accurately evaluate retrieval performance, the authors devise a new evaluation protocol that directly measures the consistency of future price movements between retrieved assets. Extensive experiments on 4,229 U.S. stocks demonstrate that FASCL significantly outperforms 13 baseline methods across all future-behavior metrics, confirming both its effectiveness and methodological innovation.

Technology Category

• Data Mining & Knowledge Management: Conversational Systems for Recommendation & Retrieval
• Search and Optimization: Learning to Search
• Computer Vision: Image and Video Retrieval

Application Category

• Search and Retrieval-Augmented AI: Web evaluation methodologies and metrics
• User Modeling, Personalization and Recommendation: Fairness-aware retrieval and ranking
• Graph Algorithms and Modeling for the Web: Querying, indexing, and retrieval in Web-related graphs

Abstract

Asset retrieval--finding similar assets in a financial universe--is central to quantitative investment decision-making. Existing approaches define similarity through historical price patterns or sector classifications, but such backward-looking criteria provide no guarantee about future behavior. We argue that effective asset retrieval should be future-aligned: the retrieved assets should be those most likely to exhibit correlated future returns. To this end, we propose Future-Aligned Soft Contrastive Learning (FASCL), a representation learning framework whose soft contrastive loss uses pairwise future return correlations as continuous supervision targets. We further introduce an evaluation protocol designed to directly assess whether retrieved assets share similar future trajectories. Experiments on 4,229 US equities demonstrate that FASCL consistently outperforms 13 baselines across all future-behavior metrics. The source code will be available soon.

Problem

• asset retrieval
• future-aligned similarity
• financial time series
• quantitative investing
• return correlation

Innovation

• Future-Aligned Learning
• Soft Contrastive Learning
• Asset Retrieval
• Representation Learning
• Financial Time Series