AppGen: Mobility-aware App Usage Behavior Generation for Mobile Users

TL;DR

AppGen is a novel autoregressive diffusion model that generates realistic mobile app usage behaviors based on users' mobility data, aiding privacy-preserving data synthesis for research and application development.

Contribution

We introduce AppGen, a diffusion-based generative model that captures complex app usage sequences from mobility data, improving data realism and utility over existing methods.

Findings

Outperforms baselines by over 12% in key metrics

Accurately models spatio-temporal app usage patterns

Generated data maintains downstream task performance

Abstract

Mobile app usage behavior reveals human patterns and is crucial for stakeholders, but data collection is costly and raises privacy issues. Data synthesis can address this by generating artificial datasets that mirror real-world data. In this paper, we propose AppGen, an autoregressive generative model designed to generate app usage behavior based on users' mobility trajectories, improving dataset accessibility and quality. Specifically, AppGen employs a probabilistic diffusion model to simulate the stochastic nature of app usage behavior. By utilizing an autoregressive structure, AppGen effectively captures the intricate sequential relationships between different app usage events. Additionally, AppGen leverages latent encoding to extract semantic features from spatio-temporal points, guiding behavior generation. These key designs ensure the generated behaviors are contextually relevant and faithfully represent users' environments and past interactions. Experiments with two real-world datasets show that AppGen outperforms state-of-the-art baselines by over 12% in critical metrics and accurately reflects real-world spatio-temporal patterns. We also test the generated datasets in applications, demonstrating their suitability for downstream tasks by maintaining algorithm accuracy and order.