App Usage Behavior Modeling and Prediction

The Tsinghua App Usage Dataset is a large-scale mobile application usage dataset collected over one week in one of China’s largest cities. It contains anonymized app usage logs from 1,000 users, capturing detailed information on 2,000 identified apps across 9,800 base stations. Each record includes user ID, timestamp, base station location, app ID, and traffic consumption, allowing for comprehensive analysis of individual and regional mobile usage patterns. This dataset has been widely applied in app usage behavior modeling, personalized app prediction, urban computing, and network traffic analysis. Previous research using this dataset has demonstrated key findings, such as the power-law distribution of app usage intervals, the high uniqueness of individual app usage patterns, and the strong correlation between app usage and location-based Points of Interest (PoIs). The dataset also provides essential metadata, including app category mapping, PoI distributions under each base station, and network traffic information, making it a valuable resource for mobile computing, recommendation systems, and human mobility studies. Researchers are encouraged to use the dataset for academic purposes while adhering to ethical guidelines prohibiting identity re-identification and commercial use.