Large Language Model-Driven Small-Capitalization Trading: Integrating Financial News Sentiment, Macroeconomic Indicators, and Technical Signals
2026-08-12 • Computation and Language
Computation and Language
AI summaryⓘ
The authors study how large language models can better analyze financial news to improve stock portfolios by using predicted risks in smarter ways. They look at breaking risk into two types and feeding this info directly into how portfolios handle risk, rather than only adjusting expected returns. Testing on small companies, they show different ways to select stocks based on macroeconomic signals and firm-specific signals perform differently at different time horizons. They find that separating these signals provides clearer guidance than combining them. Overall, portfolio construction choices and the stock selection method matter as much as the sentiment model used.
large language modelsfinancial news sentimentportfolio constructionaleatoric riskepistemic riskRussell 2000Sharpe ratiostock-selection regimerisk paritymacro indicators
Authors
Alireza Kargarzadeh, Nariman Khaledian, Navid Parvini, Arman Khaledian
Abstract
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. We study an uncertainty-aware construction that feeds model-predicted risk -- decomposed into aleatoric and epistemic components -- directly into the covariance matrix of portfolio allocators, rather than treating portfolio risk as fixed or adjusting only expected returns. We evaluate the pipeline on Russell 2000 equities under three stock-selection regimes: a pure-alpha trigger that isolates abnormal stock moves not explained by macro indicators, a pure-beta trigger that captures macro-indicator moves before the stock itself fires, and a beta trigger in which both channels agree. Across the full holding-period grid, the separated pure-alpha and pure-beta legs usually dominate the beta intersection on Sharpe and return. Two horizons are especially informative. At one day, pure beta can work under low and moderate transaction costs because it captures immediate lead-lag spillovers from liquid macro and sector indicators into exposed small-cap stocks, but this advantage disappears at 100 bps when turnover and microstructure noise dominate. At 40 days, pure beta works for a different reason: slower macro repricing overtakes the firm-specific pure-alpha channel. The strongest conservative row is pure beta with GPT-4o mini sentiment, a Student-t target, a 40-day holding period, and risk parity allocation, reaching Sharpe 2.33 at 100 bps. The results suggest that stock-selection regime and allocator choice matter at least as much as the sentiment model, and that separating firm-specific and macro-exposure triggers is more informative than requiring both to fire simultaneously.