AI Business LensTHE BUSINESS OF AI, FOR PEOPLE WHO TEACH IT OR LEARN FROM IT
NBER Working Papers · October 26, 2026 · On the brief until November 9, 2026

HouseholdBench: Evaluating Large Language Models as Predictors of Household Economic Behavior -- by Jin Huang, Diego Ferreras Garrucho, Yutong Xie, Walter M. Yuan, Qiaozhu Mei, Chen Lian, Jonathon Hazell

EconomicsBusiness Analytics
THE AI ANGLE
Predicting household economic behavior

Researchers introduced HouseholdBench to evaluate how large language models predict household economic decisions across thirty-two tasks. Gradient-boosted trees outperformed language models on most tasks, though fine-tuning helped smaller models reach proprietary levels. Economists and analysts can now compare machine learning models against standard baselines across diverse household surveys.

Summary written by AI Business Lens with an AI model from the article at nber.org. It is not the article, and the publisher has not reviewed it. For publishers.

THE TEACHING ANGLE
Gradient-boosted trees outperform large language models on most tasks, while language models produce systematic over- and underprediction errors.

Read the original at nber.org   Generate teaching or study materials

Instructors get discussion guides, assignments, and mini-cases. Students and readers get a plain summary, points to raise, an exercise, and a self-check. All built from the full article. A free account saves stories and gives you three generations. Stories stay on the brief for 14 days. After that this page keeps the link to the original.

More in Economics