Weighted Contrastive Learning for Anomaly-Aware Time-Series Forecasting
This addresses forecasting reliability under anomalies for applications like ATM logistics, but it is incremental as it builds on contrastive learning for a specific domain.
The paper tackled the problem of reliable multivariate time-series forecasting under anomalous conditions, such as sudden demand shifts in ATM cash logistics, by proposing Weighted Contrastive Adaptation (WECA), which improved SMAPE on anomaly-affected data by 6.1 percentage points compared to a baseline with negligible degradation on normal data.
Reliable forecasting of multivariate time series under anomalous conditions is crucial in applications such as ATM cash logistics, where sudden demand shifts can disrupt operations. Modern deep forecasters achieve high accuracy on normal data but often fail when distribution shifts occur. We propose Weighted Contrastive Adaptation (WECA), a Weighted contrastive objective that aligns normal and anomaly-augmented representations, preserving anomaly-relevant information while maintaining consistency under benign variations. Evaluations on a nationwide ATM transaction dataset with domain-informed anomaly injection show that WECA improves SMAPE on anomaly-affected data by 6.1 percentage points compared to a normally trained baseline, with negligible degradation on normal data. These results demonstrate that WECA enhances forecasting reliability under anomalies without sacrificing performance during regular operations.