Jiayuan Ling

Papers

Total Citations

H-Index

About

Jiayuan Ling’s research focuses on machine learning applications for real-world data challenges, particularly in user behavior analysis and anomaly detection within large-scale social platforms. Their most cited work, “A two-level stacking model for detecting abnormal users in Wechat activities” (2019), addresses the critical problem of identifying irregular user patterns amid massive, unstructured datasets. By designing a two-level stacking ensemble method, Ling improved classification accuracy for distinguishing legitimate users from abnormal ones in Wechat’s complex social ecosystem—a practical contribution that bridges algorithmic theory and business needs. With 4 citations, this paper demonstrates early impact in applied machine learning. Ling’s work is notable for tackling the “huge and disorder data pattern” problem that plagues real-world deployments, offering a scalable solution for internet platforms. Their research is particularly relevant for students and practitioners interested in fraud detection, social network analysis, and robust classification under noisy conditions. Ling’s contributions highlight the importance of model stacking in enhancing predictive performance when traditional single-model approaches fall short.