Adaptive trend analysis improves anomaly detection in time series data
AdaTrendLike: Adaptive Hierarchical Detrending and Trend Likelihood Scoring for Time Series Anomaly Detection
Artificial Intelligence
Summary
Detecting unusual patterns in data that change over time can be hard when the data includes trends that shift unpredictably. The authors describe a system, AdaTrendLike, that first separates these trends from other patterns and then checks how likely the trends are to be normal. This helps find problems more accurately and explains why something is seen as unusual. Tests on many datasets showed it works better than previous methods.
What this means in practice
- •For industrial iot operators: Detect abnormal system behaviors by analyzing changing trends in sensor data streams to improve maintenance and safety.
- •For financial data analysts: Identify unusual market trends and deviations more robustly by separating underlying trend movements in time series data.
Authors
Van Kwan Zhi Koh, Songnan Lin, Rongmo Luo, Zhiping Lin, Bihan Wen
Abstract
The rapid proliferation of Industrial Internet of Things devices has led to increasingly large-scale and non-stationary time-series data, posing significant challenges for time-series anomaly detection (TSAD). Existing approaches often focus on reconstructing or forecasting observations while overlooking the role of trend dynamics, which constitute a major source of non-stationarity and contain valuable information for anomaly identification. To address this limitation, we propose AdaTrendLike, a TSAD framework that directly estimates trend likelihoods for anomaly detection. Specifically, we introduce Standardization Embedding to capture local statistical characteristics as latent representations and AdaDetrending to adaptively decompose input series into trend and detrended components. The detrended component is processed through a Fast Fourier Transform and a complex-valued convolutional neural network to learn normal periodic patterns, while TrendEst models the distribution of the trend component. Based on the estimated distribution, TrendLike computes anomaly scores by measuring the likelihood of observed trends, enabling effective detection of deviations from normal behavior. In addition to improving detection performance, the proposed framework provides feature-level interpretability by identifying anomalies through deviations in the estimated trend distribution. Extensive experiments on five public benchmark datasets demonstrate that AdaTrendLike consistently outperforms state-of-the-art TSAD methods, validating its effectiveness and robustness across diverse application scenarios.