Xiangzhuang Shen

Hi, you can also call me Mathew Shen.

🔭 Currently, I'm a Senior Machine Learning Engineer at NetEase Fuxi, focusing on Data-Centric AI.

🔭 Previously, I worked at ByteDance as an Machine Learning Engineer in the AIOps field. My primary focus was on developing and implementing algorithms for time series forecasting, anomaly detection, and root cause analysis. The main objective was to proactively detect system failures and swiftly identify root causes, thereby reducing Mean Time To Repair (MTTR) through the analysis of Metrics, Logs, and Traces.

🔭 Prior to ByteDance, I contributed to algorithm research in network security (risk management) at Tencent. My work centered on developing anomaly detection algorithms leveraging association analysis and subspace clustering techniques, with a primary application in anti-robot systems. I take pride in the effectiveness of our algorithms, which successfully intercepted numerous attacks. I'm deeply grateful to my mentor, Mr. Liao, whose extensive experience in the security field significantly enhanced my professional growth.

🔭 My academic background is in statistics, having earned both my undergraduate degree from Hainan University (HNU) and my graduate degree from Sun Yat-sen University (SYSU)) in this field.

Publications

HEAL: Performance Troubleshooting Deep inside Data Center Hosts

Yicheng Pan, Yang Zhang, Tingzhu Bi, Linlin Han, Yu Zhang, Meng Ma, Xiangzhuang Shen, Xinrui Jiang, Feng Wang, Xian Liu, Ping Wang

ACM SIGMETRICS Performance Evaluation Review, 2024

G-Cause: Parameter-free Global Diagnosis for Hyperscale Web Service Infrastructures

Xinrui Jiang, Yang Zhang, Tingzhu Bi, Xiangzhuang Shen, Yu Zhang, Yicheng Pan, Meng Ma, Linlin Han, Feng Wang, Xian Liu, Ping Wang

2024 IEEE International Conference on Web Services (ICWS)

A Dataset for the Validation of Truth Inference Algorithms Suitable for Online Deployment

Fei Wang, Haoyu Liu, Haoyang Bi, Xiangzhuang Shen, Renyu Zhu, Runze Wu, Minmin Lin, Tangjie Lv, Changjie Fan, Qi Liu, Zhenya Huang, Enhong Chen

arXiv preprint arXiv:2403.08826