W
Wen-Ling Hsu
Researcher at AT&T Labs
Publications - 16
Citations - 181
Wen-Ling Hsu is an academic researcher from AT&T Labs. The author has contributed to research in topics: Cellular network & Service provider. The author has an hindex of 5, co-authored 13 publications receiving 138 citations.
Papers
More filters
Proceedings ArticleDOI
Characterizing data usage patterns in a large cellular network
Yu Jin,Nick Duffield,Alexandre Gerber,Patrick Haffner,Wen-Ling Hsu,Guy Jacobson,Subhabrata Sen,Shobha Venkataraman,Zhi-Li Zhang +8 more
TL;DR: This paper investigates the usage patterns of mobile data users and provides a fine-grained categorization of data users based on their usage patterns and sheds light on the potential impact of different users on the cellular data network.
Proceedings ArticleDOI
Isolating and analyzing fraud activities in a large cellular network via voice call graph analysis
TL;DR: This work develops a novel methodology for detecting voice-related fraud activities using only call records, advances the notion of voice call graphs to represent voice calls from domestic callers to foreign recipients and proposes a Markov Clustering based method for isolating dominant fraud activities from these international calls.
Proceedings ArticleDOI
Cellular Network Traffic Prediction Incorporating Handover: A Graph Convolutional Approach
Shuai Zhao,Xiaopeng Jiang,Guy Jacobson,Rittwik Jana,Wen-Ling Hsu,Raif M. Rustamov,Manoop Talasila,Syed Anwar Aftab,Yi Chen,Cristian Borcea +9 more
TL;DR: A new prediction model, STGCN-HO, that uses the transition probability matrix of the handover graph to improve traffic prediction and outperforms existing solutions in terms of prediction accuracy is proposed.
Proceedings ArticleDOI
Making sense of customer tickets in cellular networks
Yu Jin,Nick Duffield,Alexandre Gerber,Patrick Haffner,Wen-Ling Hsu,Guy Jacobson,Subhabrata Sen,Shobha Venkataraman,Zhi-Li Zhang +8 more
TL;DR: It is shown that most calls are due to customer-side factors and can be well captured by the model, and it is demonstrated that location-specific deviations from the model provide a good indicator of potential network-side issues.
Proceedings ArticleDOI
Speaking with Actions - Learning Customer Journey Behavior
TL;DR: This paper proposes a systematic two-step framework based on omni-channel care journey data and customer profile data that predicts whether or not a customer will contact in the time period directly following the recent contacts and clusters the action embedding learned by the model and investigates the intrinsic properties of customer behavior.