Bridging Human Expertise and AI

Abstract

This study investigates the role of large language models (LLMs) in retail investors (RIs) decision-making processes from the perspective of the Theory of Planned Behaviour (TPB). It explores whether LLMs can replace or change the role of financial experts and whether introducing LLMs may lead to more infromed RIs’ decisions. Qualitative interviews were conducted with experienced RIs (n = 8). Secondary data were gathered from YouTube recordings (n = 44). Thematic analysis and Retrieval-Augmented Generation (RAG) methodology was used for data extraction and analysis of the scripts. The findings indicate that while LLMs have the potential to enhance accessibility to expert opinions and provide more informed investment decisions, they are unlikely to replace human experts. RIs show a preference for combining LLM insights with human expertise, recognising the limitations of LLMs in managing complex and nuanced investment information. The study highlights the usefulness of the TPB as a framework for the exploration of the topic. It also introduces a novel research method - advanced data extraction techniques on a vast unstructured dataset.?Results contribute to the understanding of LLMs potential in supporting RIs and confirms the usefulness on the AESTIMA tool for data extraction and analysis.

Ähnliche Arbeiten