ATHENS — Researchers from the University of Georgia and the University of Rome Tor Vergata conducted a study in August 2025 examining seven generative artificial intelligence (GenAI) platforms. The study investigated the consistency of financial advice provided by these platforms when presented with prompts varied by race and gender.

The academic paper, authored by finance professors Swarn Chatterjee, Brenda Cude, and Gianni Nicolini, was published last month in the Journal of Financial Planning. They queried free-access versions of ChatGPT, Claude, Copilot, DeepSeek, Gemini, Meta AI, and Perplexity using the same set of prompts related to emergency savings, optimal retirement savings withdrawal rates, and recommended investment portfolio composition.

Researchers altered the hypothetical individual's race and gender in the prompts to observe any changes in the GenAI recommendations. The study found variation in how GenAI responded to questions about emergency savings, asset allocation, and retirement portfolio withdrawals. "Although the tools often produced recommendations that broadly aligned with generic financial planning principles, such as the 4 percent retirement withdrawal rule, there were significant differences across platforms in suggested emergency savings and portfolio allocations," Chatterjee, Cude, and Nicolini said.

"GenAI-driven responses may sound confident but can still be incomplete, misleading, or incorrect," the authors said. "The findings suggest that GenAI may serve as a helpful starting point for consumers but should complement, not replace, professional financial advice."

A September Intuit Credit Karma survey indicated that 66% of Americans who have used GenAI leveraged it for financial advice. This figure rose to 82% for both Gen Z and millennials. AI does not owe a fiduciary duty to users.

A 2024 study published in the Journal of Risk and Financial Management also examined ChatGPT's capacity to offer financial advice. That study found that ChatGPT's recommendations were generic and frequently overlooked pertinent information.