Confidence-Driven Augmentation of Synthetic Survey Data

Research unit

INNOSUISSE

Project number

125.426 IP-SBM

Project title

Confidence-Driven Augmentation of Synthetic Survey Data

Texts for this project

	German	French	Italian	English
Key words	-	-	-
Abstract	-	-	-

Category	Text
Key words (English)	Social sciences & business management, New media
Abstract (English)	Market research remains costly and slow. This research combines LLM-based synthetic survey data with human data where most needed. Compared to human random samples, the method cuts paid human samples by 20% while preserving accuracy, enabling affordable, timely market research and political polling.