Forecasting Anomaly Precursors via Uncertainty-Aware Time-Series Ensembles

2026-02-18

AI Summary

This work addresses the limitation of existing time series anomaly detection methods, which predominantly rely on reactive responses and struggle to provide proactive early warnings. To overcome this, we propose FATE, a novel framework that, for the first time, incorporates ensemble predictive uncertainty into unsupervised anomaly precursor detection. FATE constructs a diverse ensemble of forecasting models and quantifies their prediction divergence to identify early signs of anomalies. We further introduce PTaPR, a new evaluation metric that holistically assesses the accuracy, coverage, and timeliness of early warnings. Extensive experiments on five real-world datasets demonstrate that FATE achieves an average improvement of 19.9 percentage points in PTaPR AUC and a 20.02 percentage point gain in early-detection F1 score, significantly outperforming current state-of-the-art baselines.

Technology Category

• Machine Learning: Ensemble Methods
• Data Mining & Knowledge Management: Anomaly/Outlier Detection
• Reasoning under Uncertainty: Sequential Decision Making

Application Category

• Search and Retrieval-Augmented AI: Web evaluation methodologies and metrics
• User Modeling, Personalization and Recommendation: Fairness-aware retrieval and ranking
• Web Mining and Content Analysis: Large pretrained models with web data

Abstract

Detecting anomalies in time-series data is critical in domains such as industrial operations, finance, and cybersecurity, where early identification of abnormal patterns is essential for ensuring system reliability and enabling preventive maintenance. However, most existing methods are reactive: they detect anomalies only after they occur and lack the capability to provide proactive early warning signals. In this paper, we propose FATE (Forecasting Anomalies with Time-series Ensembles), a novel unsupervised framework for detecting Precursors-of-Anomaly (PoA) by quantifying predictive uncertainty from a diverse ensemble of time-series forecasting models. Unlike prior approaches that rely on reconstruction errors or require ground-truth labels, FATE anticipates future values and leverages ensemble disagreement to signal early signs of potential anomalies without access to target values at inference time. To rigorously evaluate PoA detection, we introduce Precursor Time-series Aware Precision and Recall (PTaPR), a new metric that extends the traditional Time-series Aware Precision and Recall (TaPR) by jointly assessing segment-level accuracy, within-segment coverage, and temporal promptness of early predictions. This enables a more holistic assessment of early warning capabilities that existing metrics overlook. Experiments on five real-world benchmark datasets show that FATE achieves an average improvement of 19.9 percentage points in PTaPR AUC and 20.02 percentage points in early detection F1 score, outperforming baselines while requiring no anomaly labels. These results demonstrate the effectiveness and practicality of FATE for real-time unsupervised early warning in complex time-series environments.

Problem

• anomaly detection
• time-series forecasting
• early warning
• predictive uncertainty
• unsupervised learning

Innovation

• anomaly forecasting
• predictive uncertainty
• time-series ensembles
• precursor detection
• unsupervised early warning