Regret-Driven Portfolios: LLM-Guided Smart Clustering for Optimal Allocation

TL;DR

This paper introduces a novel LLM-guided portfolio allocation framework that combines online learning, market sentiment, and LLM-based hedging to improve risk-adjusted returns for investors.

Contribution

It presents a new no-regret portfolio method integrating sentiment analysis and LLM-driven downside protection, enhancing traditional online learning approaches.

Findings

Outperforms SPY buy-and-hold by 69% in annualized returns.

Increases Sharpe ratio by 119%.

Demonstrates effectiveness for risk-averse investors.

Abstract

We attempt to mitigate the persistent tradeoff between risk and return in medium- to long-term portfolio management. This paper proposes a novel LLM-guided no-regret portfolio allocation framework that integrates online learning dynamics, market sentiment indicators, and large language model (LLM)-based hedging to construct high-Sharpe ratio portfolios tailored for risk-averse investors and institutional fund managers. Our approach builds on a follow-the-leader approach, enriched with sentiment-based trade filtering and LLM-driven downside protection. Empirical results demonstrate that our method outperforms a SPY buy-and-hold baseline by 69% in annualized returns and 119% in Sharpe ratio.