LLM-Enhanced Black-Litterman Portfolio Optimization
This work addresses a key bottleneck in portfolio optimization for investors by providing a systematic method to incorporate LLM-based views, though it is incremental as it builds on the existing Black-Litterman framework.
This study tackled the challenge of systematically generating investor views for the Black-Litterman portfolio optimization model by using Large Language Models (LLMs) to translate return forecasts and predictive uncertainty into views and confidence levels, resulting in portfolios that significantly outperformed traditional baselines on S&P 500 constituents in both absolute and risk-adjusted terms.
The Black-Litterman model addresses the sensitivity issues of tra- ditional mean-variance optimization by incorporating investor views, but systematically generating these views remains a key challenge. This study proposes and validates a systematic frame- work that translates return forecasts and predictive uncertainty from Large Language Models (LLMs) into the core inputs for the Black-Litterman model: investor views and their confidence lev- els. Through a backtest on S&P 500 constituents, we demonstrate that portfolios driven by top-performing LLMs significantly out- perform traditional baselines in both absolute and risk-adjusted terms. Crucially, our analysis reveals that each LLM exhibits a dis- tinct and consistent investment style which is the primary driver of performance. We found that the selection of an LLM is therefore not a search for a single best forecaster, but a strategic choice of an investment style whose success is contingent on its alignment with the prevailing market regime. The source code and data are available at https://github.com/youngandbin/LLM-BLM.