Timezone: »

 
Towards an Efficient Algorithm for Time Series Forecasting with Anomalies
Hao Cheng · Qingsong Wen · Yang Liu · Liang Sun

@
in DMLR Workshop: Data-centric Machine Learning Research »

Most of time series forecasting techniques assume that the training data is clean without anomalies. This assumption is unrealistic since the collected time series data can be contaminated in practice. The forecasting model will be inferior if it is directly trained by time series with anomalies. In this paper, we aim to develop methods to automatically learn a robust forecasting model from a data-centric perspective. Specifically, we first statistically define three types of anomalies in time series data, then theoretically and experimentally analyze the \emph{loss robustness} and \emph{sample robustness} when these anomalies exist. Based on our analyses, we propose a simple and efficient algorithm to learn a robust forecasting model which outperforms all existing approaches.

Author Information

Hao Cheng (University of California, Santa Cruz)
Qingsong Wen (Alibaba Group (U.S.) Inc.)

I work at Alibaba DAMO Academy-Decision Intelligence Lab as a Staff Engineer / Researcher / Manager at Greater Seattle Area, WA, USA, working on Intelligent Time Series and Decision (AI for Time Series, AIOps) for Cloud Computing, E-Commerce, and Energy Industry.

Yang Liu (UC Santa Cruz/ByteDance Research)
Liang Sun (Alibaba Group)

More from the Same Authors