This content originally appeared on NN/g latest articles and announcements and was authored by Raluca Budiu
Summary: AI-simulated users can fill in missing data and predict population-level trends. They perform better when they are based on extensive contextual information.
Can AI-powered models replace real people in user research? A growing body of research is exploring whether digital twins (generative AI models designed to simulate individual users) and synthetic users (models that mimic broader user groups) can replicate real human responses. In UX, these technologies raise exciting possibilities for scaling research, filling in gaps, and running studies that might otherwise be too slow or expensive.
In this article, I examine three recent studies that put digital twins and synthetic users to the test. I review at how they were built, what kinds of tasks they performed, and how closely their results matched real human data.
TL;DR
Don’t care about the full details of each study? Here are the key findings.
Read Full Article
This content originally appeared on NN/g latest articles and announcements and was authored by Raluca Budiu
Raluca Budiu | Sciencx (2025-08-15T17:00:00+00:00) Evaluating AI-Simulated Behavior: Insights from Three Studies on Digital Twins and Synthetic Users. Retrieved from https://www.scien.cx/2025/08/15/evaluating-ai-simulated-behavior-insights-from-three-studies-on-digital-twins-and-synthetic-users/
Please log in to upload a file.
There are no updates yet.
Click the Upload button above to add an update.