Investor risk profiles of large language models
Fuente:
arXiv
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866916054771433472 |
|---|---|
| author | Cho, Hanyong Bae, Geumil Kim, Jang Ho |
| author_facet | Cho, Hanyong Bae, Geumil Kim, Jang Ho |
| contents | This paper investigates how large language models (LLMs) form and express investor risk profiles, a critical component of retail investment advising. We examine three LLMs (GPT, Gemini, and Llama) and assess their responses to a standardized risk questionnaire under varying prompts. In particular, we establish each model's default investment profile by analyzing repeated responses per model. We observe that LLMs are generally longterm investors but exhibit different tendencies in risk tolerance: Gemini has a moderate risk level with highly consistent responses, Llama skews more conservative, and GPT appears moderately aggressive with the greatest variation in answers. Moreover, we find that assigning specific personas such as age, wealth, and investment experience leads each LLM to adjust its risk profile, although the extent of these adjustments differs across the models. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2603_09303 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Investor risk profiles of large language models Cho, Hanyong Bae, Geumil Kim, Jang Ho Portfolio Management This paper investigates how large language models (LLMs) form and express investor risk profiles, a critical component of retail investment advising. We examine three LLMs (GPT, Gemini, and Llama) and assess their responses to a standardized risk questionnaire under varying prompts. In particular, we establish each model's default investment profile by analyzing repeated responses per model. We observe that LLMs are generally longterm investors but exhibit different tendencies in risk tolerance: Gemini has a moderate risk level with highly consistent responses, Llama skews more conservative, and GPT appears moderately aggressive with the greatest variation in answers. Moreover, we find that assigning specific personas such as age, wealth, and investment experience leads each LLM to adjust its risk profile, although the extent of these adjustments differs across the models. |
| title | Investor risk profiles of large language models |
| topic | Portfolio Management |
| url | https://arxiv.org/abs/2603.09303 |