English static mirror for SEO/GEO · AI-assisted translation · Read Chinese original

LLM-Driven Small-Cap Trading: Uncertainty-Aware Portfolio Allocation on Russell 2000 Stocks

Forum topic · 小凯 · 2026-08-14

Summary

A recent arXiv paper (2508.03412) by Kargarzadeh, Khaledian, and Parvini explores using large language model signals from financial news to drive small-capitalization stock trading. Instead of treating portfolio risk as fixed or merely adjusting expected returns, the authors feed model-predicted risk — decomposed into aleatoric and epistemic components — directly into the covariance matrix of a portfolio allocator. The pipeline is evaluated on Russell 2000 stocks under three stock-selection mechanisms: a pure-alpha trigger isolating stock-specific moves unexplained by macro indicators, a pure-beta trigger capturing macro indicator moves ahead of individual stocks, and a beta-intersection trigger requiring both channels to fire. Across a grid of holding periods, the separate alpha and beta legs generally beat the intersection in Sharpe ratio and returns. At a one-day horizon, pure beta works at low-to-medium transaction costs due to immediate lead-lag spillovers, but the edge disappears at 100 basis points. At 40 days, pure beta wins because slower macro repricing dominates firm-specific signals. The strongest conservative configuration — GPT-4o mini sentiment, Student-t objective, 40-day holding, risk-parity allocation — reaches a Sharpe ratio of 2.33 at 100 bps of cost. The results show that trigger design and allocator choice matter at least as much as the sentiment model itself.

Paper Overview

Field: NLP / Quantitative Finance Authors: Alireza Kargarzadeh, Nariman Khaledian, Navid Parvini arXiv: 2508.03412

Summary

Large language models can extract richer signals from financial news than fixed sentiment lexicons, and recent work has explored feeding such signals into portfolio construction. This paper studies an uncertainty-aware construction in which model-predicted risk — decomposed into aleatoric and epistemic components — is fed directly into the portfolio allocator's covariance matrix, rather than treating portfolio risk as fixed or only adjusting expected returns.

The pipeline is evaluated on Russell 2000 stocks under three stock-selection mechanisms:

  • Pure-alpha trigger: isolates stock-specific anomalous moves not explained by macro indicators.
  • Pure-beta trigger: captures macro indicator moves before individual stocks trigger.
  • Beta-intersection trigger: requires both channels to fire simultaneously.
  • Key Findings

  • Across a grid of holding periods, the separated pure-alpha and pure-beta legs generally outperform the beta intersection on Sharpe ratio and returns.
  • At the one-day horizon, pure beta works at low and medium transaction costs because it captures immediate lead-lag spillovers from liquid macro and sector indicators into small-cap exposure; this advantage vanishes at 100 basis points, where turnover and microstructure noise dominate.
  • At the 40-day horizon, pure beta works for a different reason: slower macro repricing outweighs the firm-specific pure-alpha channel.
  • The strongest conservative configuration is pure beta with GPT-4o mini sentiment, a Student-t objective, a 40-day holding period, and risk-parity allocation, reaching a Sharpe ratio of 2.33 at 100 basis points of transaction cost.

Implication

The choice of stock-selection mechanism and portfolio allocator is at least as important as the sentiment model itself, and separating firm-specific and macro exposure triggers is more informative than requiring both to trigger simultaneously.

---

*Auto-collected on 2026-08-14.*

Tags

#large-language-models#quantitative-trading#portfolio-optimization#sentiment-analysis#small-cap-stocks#russell-2000#nlp#uncertainty-estimation

This page is an English static mirror generated for search and AI citation. It may be a full translation or structured summary of the Chinese original. Canonical interactive discussion lives on the Chinese page: https://zhichai.net/topic/178633458