Improving Robustness on Seasonality-Heavy Multivariate Time Series Anomaly Detection

Robust Anomaly Detection (AD) on time series data is a key component for monitoring many complex modern systems. These systems typically generate high-dimensional time series that can be highly noisy, seasonal, and inter-correlated. This paper explores some of the challenges in such data, and proposes a new approach that makes inroads towards increased robustness on seasonal and contaminated data, while providing a better root cause identification of anomalies. In particular, we propose the use of Robust Seasonal Multivariate Generative Adversarial Network (RSM-GAN) that extends recent advancements in GAN with the adoption of convolutional-LSTM layers and attention mechanisms to produce excellent performance on various settings. We conduct extensive Figure 1: RSM-GAN architecture with loss definitions experiments in which not only do this model displays more robust behavior on complex seasonality patterns, but also shows increased resistance to training data contamination. We compare it with existing often produce multi-channel time series data that automatically classical and deep-learning AD models, and show that this detecting anomalous moments can be quite challenging to any architecture is associated with the lowest false positive rate and anomaly detection (AD) system due to its intrinsic inter-correlation, improves precision by 30% and 16% in real-world and synthetic seasonality, trendiness, and irregularity traits.