Large language model as user daily behavior data generator: balancing population diversity and individual personality
This work addresses privacy and data availability issues in behavior prediction for users, though it is incremental as it applies existing LLMs to a new domain.
The authors tackled the challenge of predicting human daily behavior while addressing privacy concerns by introducing BehaviorGen, a framework that uses large language models to generate synthetic behavior data. They achieved improvements of up to 18.9% in human mobility and smartphone usage predictions through data augmentation and replacement.
Predicting human daily behavior is challenging due to the complexity of routine patterns and short-term fluctuations. While data-driven models have improved behavior prediction by leveraging empirical data from various platforms and devices, the reliance on sensitive, large-scale user data raises privacy concerns and limits data availability. Synthetic data generation has emerged as a promising solution, though existing methods are often limited to specific applications. In this work, we introduce BehaviorGen, a framework that uses large language models (LLMs) to generate high-quality synthetic behavior data. By simulating user behavior based on profiles and real events, BehaviorGen supports data augmentation and replacement in behavior prediction models. We evaluate its performance in scenarios such as pertaining augmentation, fine-tuning replacement, and fine-tuning augmentation, achieving significant improvements in human mobility and smartphone usage predictions, with gains of up to 18.9%. Our results demonstrate the potential of BehaviorGen to enhance user behavior modeling through flexible and privacy-preserving synthetic data generation.