AI financial advice is surprisingly good — especially if you ask the right questions | MIT Sloan
Skip to main content
Get MIT Sloan's latest expert insights in your inbox.<br>Sign up for the MIT Sloan Thinking Forward newsletter.
contact
Search<br>Main Menu
close search
MBA<br>A full-time, two-year MBA program.
Leaders for Global Operations<br>A two-year, dual-degree program awarding an MBA from MIT Sloan and an SM from MIT School of Engineering.
MBA Early (Deferred admissions option)<br>Deferred admission program; candidates work two to five years before enrolling in the MBA program.
MIT Sloan Evening MBA<br>An MBA program designed for working professionals.
Master of Finance<br>A 12- or 18-month graduate program in finance.
Master of Business Analytics<br>A 12-month graduate program in business analytics.
PhD<br>A doctoral program that researches management science, economics, finance, marketing, operations, strategy, and other business disciplines.
Undergraduate<br>Undergraduate degrees offered in management, business analytics, and finance.
Master of Science in Management Studies<br>Combine an international MBA with a graduate degree in management science; available to partner and affiliate school students only.
Executive<br>Programs
MIT Executive MBA<br>A 20-month executive MBA program for mid-career professionals.
MIT Sloan Fellows MBA<br>A one-year, full-time MBA program for mid-career professionals.
System Design & Management<br>A master's degree program combining engineering and management for mid-career professionals.
Executive Education<br>Non-degree programs for senior executives and high-potential managers.
Visiting Fellows<br>A non-degree, customizable program for mid-career professionals.
People are increasingly turning to artificial intelligence for financial advice, but will following it improve their financial standing?
AI at WorkResearch and insights powering the intersection of AI and business, delivered monthly.
Yes, I’d also like to subscribe to the Thinking Forward newsletter
Leave this field blank
“Half of Americans say they are using AI to get financial advice, but we know very little about what kind of advice they’re getting and whether they’re acting on it,” said Taha Choukhmane, an assistant professor of finance at the MIT Sloan School of Management and co-author of a new paper that measures and analyzes the quality of financial advice given by large language models.<br>Research by Choukhmane and co-authors showed that following AI recommendations can result in sizable saving buffers for virtually all individuals above age 30.<br>AI consistently advised people to save during their working years, draw down savings in retirement, invest heavily in diversified stock funds, and reduce stock exposure after age 45. However, AI chatbots were less successful in adjusting to shocks like unemployment, and they allowed portfolios to drift rather than actively rebalancing them.<br>The quality of financial advice given by LLMs improved when the researchers introduced more structured prompts, but the AI still often generated too little active portfolio rebalancing.<br>How the study was conducted<br>The researchers built a model reflecting how people’s incomes, jobs, investments, and taxes typically evolve over their lives, which gave them a benchmark for what “good” financial decisions look like.<br>Then they asked a sample of 1,000 adults to write their own prompts seeking spending and investing advice from GPT-5.2, GPT-5.6, or Gemini 3 Flash.<br>Next, they simulated what would happen if people from 22 to 89 years of age followed that advice over time, repeatedly asking AI these same types of questions and following its advice on spending, saving, and investing.
How the researchers define “academic prompt”<br>An academic prompt is one that asks the LLM to give regulated professional financial advice, references life cycle planning and the user’s best interests, and provides explicit information about all of the simulated individual’s relevant financial conditions and explicit assumptions about the economic environment.
Learn More<br>Collapse
Finally, they repeated the exercise using well-written academic prompts that included full financial information and clear assumptions. These more-detailed prompts included information on the individual’s age, job status, income, and savings balances, along with assumptions about the economic environment.<br>The authors compared the simulated advice (what would happen if regular people followed the AI recommendations from the prompts they gave) to what people were already doing financially without the help of AI. They also compared the simulated advice to the academic prompt.<br>The results showed that LLMs can offer an affordable, widely accessible source of financial guidance that can help users overcome the significant costs, biases, and conflicts of interest associated with traditional human financial advisors.<br>Breaking down the findings<br>Overall, the researchers found that the financial advice...