AA-Forecast: Anomaly-Aware Forecast for Extreme Events
This work addresses risk management in time series forecasting for extreme events, offering an incremental improvement by automating anomaly detection and integration.
The paper tackles the challenge of probabilistic forecasting for extreme events like hurricanes and pandemics by proposing an anomaly-aware framework that automatically detects and incorporates anomalies to improve prediction accuracy, demonstrating consistent superior accuracy with less uncertainty on three datasets.
Time series models often deal with extreme events and anomalies, both prevalent in real-world datasets. Such models often need to provide careful probabilistic forecasting, which is vital in risk management for extreme events such as hurricanes and pandemics. However, it is challenging to automatically detect and learn to use extreme events and anomalies for large-scale datasets, which often require manual effort. Hence, we propose an anomaly-aware forecast framework that leverages the previously seen effects of anomalies to improve its prediction accuracy during and after the presence of extreme events. Specifically, the framework automatically extracts anomalies and incorporates them through an attention mechanism to increase its accuracy for future extreme events. Moreover, the framework employs a dynamic uncertainty optimization algorithm that reduces the uncertainty of forecasts in an online manner. The proposed framework demonstrated consistent superior accuracy with less uncertainty on three datasets with different varieties of anomalies over the current prediction models.