This article introduces ConsumerSim, a generative framework that reconstructs Consumer Confidence Index (CCI) dynamics using a microdata-calibrated synthetic population and various economic signals. The model ranks first among baselines for reconstruction accuracy across U.S., EU27, and Japanese CCI series, particularly during high-salience shocks.
- ConsumerSim utilizes time-stamped macroeconomic, financial, policy, and news signals alongside survey-like response generation.
- It achieves superior performance in persistence, time-series, regression, and information-augmented reconstruction metrics.
- The reconstructed signal improves short-horizon prediction of real activity, especially housing outcomes.
- Mechanism analyses reveal that CCI movements concentrate around salient events and vary by income, homeownership, education, and political alignment.
- Representative aggregation, situational signals, persona heterogeneity, and inertia are identified as necessary for accuracy and diagnosis.
The findings support a behavioral view of consumer confidence as an interpretable Human-Environment response process rather than a purely aggregate time series.