Can ChatGPT Improve Investment Decision? From a portfolio management perspective

ChatGPT as a large language model (LLM) has recently gained significant attention for generating human-like text. While much of the existing research has focused on its applications for writing and language translation, the potential of ChatGPT in finance, particularly in the context of investment, remains unexplored. This research aims to examine the efficacy of ChatGPT in aiding portfolio management with regard to asset allocation and diversification through the use of a quantitative methodology. We use ChatGPT to select asset classes and evaluate the diversification effect of its selections. Our results suggest that ChatGPT’s selections are statistically significantly better in terms of diversity index than randomly selected assets. We also construct portfolios based on ChatGPT’s selections and find that they outperform portfolios built on randomly selected assets. Overall, our study contributes to a better understanding of the role of LLMs like ChatGPT as potential assistants for portfolio managers.