arXiv Open Access 2025

Evaluating AI for Finance: Is AI Credible at Assessing Investment Risk?

Divij Chawla Ashita Bhutada Do Duc Anh Abhinav Raghunathan Vinod SP +6 lainnya
Lihat Sumber

Abstrak

We assess whether AI systems can credibly evaluate investment risk appetite-a task that must be thoroughly validated before automation. Our analysis was conducted on proprietary systems (GPT, Claude, Gemini) and open-weight models (LLaMA, DeepSeek, Mistral), using carefully curated user profiles that reflect real users with varying attributes such as country and gender. As a result, the models exhibit significant variance in score distributions when user attributes-such as country or gender-that should not influence risk computation are changed. For example, GPT-4o assigns higher risk scores to Nigerian and Indonesian profiles. While some models align closely with expected scores in the Low- and Mid-risk ranges, none maintain consistent scores across regions and demographics, thereby violating AI and finance regulations.

Topik & Kata Kunci

Penulis (11)

D

Divij Chawla

A

Ashita Bhutada

D

Do Duc Anh

A

Abhinav Raghunathan

V

Vinod SP

C

Cathy Guo

D

Dar Win Liew

P

Prannaya Gupta

R

Rishabh Bhardwaj

R

Rajat Bhardwaj

S

Soujanya Poria

Format Sitasi

Chawla, D., Bhutada, A., Anh, D.D., Raghunathan, A., SP, V., Guo, C. et al. (2025). Evaluating AI for Finance: Is AI Credible at Assessing Investment Risk?. https://arxiv.org/abs/2505.18953

Akses Cepat

Lihat di Sumber
Informasi Jurnal
Tahun Terbit
2025
Bahasa
en
Sumber Database
arXiv
Akses
Open Access ✓