GraphAD: A Graph Neural Network for Entity-Wise Multivariate Time-Series Anomaly Detection

TL;DR

GraphAD is a novel graph neural network-based model designed for entity-wise multivariate time-series anomaly detection, effectively capturing entity-specific patterns and outperforming existing methods on real-world business data.

Contribution

The paper introduces GraphAD, a new GNN-based approach for entity-specific anomaly detection in multivariate time-series, addressing limitations of traditional methods.

Findings

GraphAD outperforms existing anomaly detection methods on real-world data.

Decomposes KPIs into stable and volatile components for better pattern extraction.

Constructs a new dataset for entity-wise multivariate time-series anomaly detection.

Abstract

In recent years, the emergence and development of third-party platforms have greatly facilitated the growth of the Online to Offline (O2O) business. However, the large amount of transaction data raises new challenges for retailers, especially anomaly detection in operating conditions. Thus, platforms begin to develop intelligent business assistants with embedded anomaly detection methods to reduce the management burden on retailers. Traditional time-series anomaly detection methods capture underlying patterns from the perspectives of time and attributes, ignoring the difference between retailers in this scenario. Besides, similar transaction patterns extracted by the platforms can also provide guidance to individual retailers and enrich their available information without privacy issues. In this paper, we pose an entity-wise multivariate time-series anomaly detection problem that considers the time-series of each unique entity. To address this challenge, we propose GraphAD, a novel multivariate time-series anomaly detection model based on the graph neural network. GraphAD decomposes the Key Performance Indicator (KPI) into stable and volatility components and extracts their patterns in terms of attributes, entities and temporal perspectives via graph neural networks. We also construct a real-world entity-wise multivariate time-series dataset from the business data of Ele.me. The experimental results on this dataset show that GraphAD significantly outperforms existing anomaly detection methods.