Hello, I'm Wenjie Hu

Time series modeling has attracted extensive research efforts; however, achieving both reliable efficiency and interpretability from a unified model still remains a challenging problem.

Our recent work proposes to model time series from the perspective of graphs. More specifically, we aim to capture the representative patterns (or referred to as states) and their transitions underpinning the observed time series, and describe how these factors affect the time series evolution. To achieve this, we respectively propose the shapelet based method (Time2Graph, Cheng et al., AAAI'20) and a dynamic graph neural network based model (EvoNet, Hu et al., WSDM'21). Our proposed methods not only achieves clear improvements comparing with state-of-the-art baselines in many tasks, but also provide valuable insights towards explaining the results of prediction results.

Our work has been applied in real-world scenarios, such as anomaly detection of time series, as a common service of Alibaba Cloud, collaborated with SLS, Alibaba Cloud, Alibaba Group. Currently our algorithm have served hundreds of enterprise users. ( Hu et al., WSDM'21, Cheng et al., AAAI'20) [Project Homepage]

Electricity theft, the behavior that involves users conducting illegal operations on electrical meters to avoid individual electricity bills, is a common phenomenon in the developing countries. Considering its harmfulness to both power grids and the public, substantial effort has been expended to prevent or detect these behaviors.

To explore the patterns of electricity theft hidden in the large-scale users, we conduct a deep study on the multi-source data: in addition to users’ electricity usage records, we analyze user behaviors by means of regional factors (non-technical loss) and climatic factors (temperature) in the corresponding transformer area. Our results unearth several interesting patterns: electricity thieves are likely to consume much more electrical power than normal users, especially under extremely high or low temperatures. Motivated by these empirical observations, a novel hierarchical framework is designed for identifying electricity thieves. (Hu et al., WWW'20)