Using GPT-4 for Financial Advice

18 Pages Posted: 6 Jul 2023

See all articles by Christian Fieberg

Christian Fieberg

City University of Applied Sciences

Lars Hornuf

Technische Universität Dresden; CESifo (Center for Economic Studies and Ifo Institute)

David Streich

Catholic University of Eichstaett-Ingolstadt - Ingolstadt School of Management

Date Written: 2023

Abstract

We show that the recently released text-based artificial intelligence tool GPT-4 can provide suitable financial advice. The tool suggests specific investment portfolios that reflect an investor’s individual circumstances such as risk tolerance, risk capacity, and sustainability preference. Notably, while the suggested portfolios display home bias and are rather insensitive to the investment horizon, historical risk-adjusted performance is on par with a professionally managed benchmark portfolio. Given the current inability of GPT-4 to provide full-service financial advice, it may be used by financial advisors as a back-office tool for portfolio recommendation.

Keywords: GPT-4, ChatGPT, financial advice, artificial intelligence, portfolio management

JEL Classification: G000, G110

Suggested Citation

Fieberg, Christian and Hornuf, Lars and Streich, David, Using GPT-4 for Financial Advice (2023). CESifo Working Paper No. 10529, Available at SSRN: https://ssrn.com/abstract=4499485 or http://dx.doi.org/10.2139/ssrn.4499485

Christian Fieberg (Contact Author)

City University of Applied Sciences ( email )

Werderstr. 73
Bremen, DE Bremen 28199
Germany

Lars Hornuf

Technische Universität Dresden ( email )

Dresden, 01307
Germany

HOME PAGE: http://www.hornuf.com

CESifo (Center for Economic Studies and Ifo Institute) ( email )

Poschinger Str. 5
Munich, DE-81679
Germany

David Streich

Catholic University of Eichstaett-Ingolstadt - Ingolstadt School of Management ( email )

Finance and Banking Department
Catholic University of Eichstaett-Ingolstadt
Ingolstadt, 85049
Germany

Do you have a job opening that you would like to promote on SSRN?

Paper statistics

Downloads
513
Abstract Views
1,429
Rank
92,322
PlumX Metrics