计算机科学与探索2019，Vol.13Issue(12)：1981-1994,14.DOI:10.3778/j.issn.1673-9418.1812034
移动APP演化模式分析与预测
Evolutionary Pattern Analysis and Prediction of Mobile APP
摘要
Abstract
The popularity prediction of mobile APP (application) provides substantial value to a broad range of applications, ranging from APP development to targeted advertising. However, most previous studies do this work by establishing regression models for popularity and impact factors, or using clustering and classification algorithms. It does not fully investigate the process of popularity evolution and the reasons behind it. This paper discusses and analyzes the potential predictors, especially the impact of early evolutionary patterns on future popularity. To this end, this paper first explores six basic evolutionary patterns and six impact factors that are closely related to APP popularity. After detailed analysis, this paper presents CrowdPop, a popularity prediction model based on the random forest algorithm, to quantify patterns and factors as predictors of CrowdPop. The experiment results with a real-world dataset of 126 APPs indicate that, compared with baseline methods, the CrowdPop performs better in mobile APP popularity prediction.关键词
移动APP/演化模式/影响因素/流行度预测Key words
mobile APP/evolution pattern/impact factors/popularity prediction分类
信息技术与安全科学引用本文复制引用
张艺璇,郭斌,欧阳逸,王柱,於志文..移动APP演化模式分析与预测[J].计算机科学与探索,2019,13(12):1981-1994,14.基金项目
The National Natural Science Foundation of China under Grant Nos.61772428,61725205 (国家自然科学基金) （国家自然科学基金）
the National Key Research and Development Program of China under Grant No.2017YFB1001803 (国家重点研发计划). （国家重点研发计划）
