When Will It Fail?: Anomaly to Prompt for Forecasting Future Anomalies in Time Series

2025-06-30

AI Summary

Existing methods struggle to accurately predict the precise timestamps of future anomalies in time series, often limiting themselves to instantaneous detection or lacking the capacity to model long-horizon anomalies. This paper introduces Anomaly-to-Prompt (A2P), the first framework systematically addressing the novel task of *anomaly occurrence time prediction*. Its core contributions are: (1) a learnable anomaly prompt pool that enables signal-adaptive synthesis of diverse anomaly patterns; and (2) a joint mechanism integrating anomaly-aware forecasting with synthetic anomaly prompting, explicitly modeling temporal dependencies between historical and future anomalies. Evaluated on multiple real-world datasets, A2P achieves state-of-the-art performance in long-horizon anomaly timestamp prediction—demonstrating both high accuracy and strong robustness. The source code is publicly available.

Technology Category

• Machine Learning: Time-Series/Data Streams
• Data Mining & Knowledge Management: Anomaly/Outlier Detection
• Humans and AI: Human-Aware Planning and Behavior Prediction

Application Category

• Graph Algorithms and Modeling for the Web: Algorithms and analysis for heterogeneous, signed, attributed, multi-relational, temporal, higher-order, and annotated Web-related graphs
• Search and Retrieval-Augmented AI: Agentic search
• User Modeling, Personalization and Recommendation: Attacks and countermeasures in recommendation systems

Abstract

Recently, forecasting future abnormal events has emerged as an important scenario to tackle real-world necessities. However, the solution of predicting specific future time points when anomalies will occur, known as Anomaly Prediction (AP), remains under-explored. Existing methods dealing with time series data fail in AP, focusing only on immediate anomalies or failing to provide precise predictions for future anomalies. To address the AP task, we propose a novel framework called Anomaly to Prompt (A2P), comprised of Anomaly-Aware Forecasting (AAF) and Synthetic Anomaly Prompting (SAP). To enable the forecasting model to forecast abnormal time points, we adopt a strategy to learn the relationships of anomalies. For the robust detection of anomalies, our proposed SAP introduces a learnable Anomaly Prompt Pool (APP) that simulates diverse anomaly patterns using signal adaptive prompt. Comprehensive experiments on multiple real-world datasets demonstrate the superiority of A2P over state-of-the-art methods, showcasing its ability to predict future anomalies. Our implementation code is available at https://github.com/KU-VGI/AP.

Problem

• Predicting future anomaly time points in time series
• Addressing limitations of existing anomaly detection methods
• Learning anomaly relationships for robust future forecasting

Innovation

• Anomaly-Aware Forecasting learns anomaly relationships
• Synthetic Anomaly Prompting simulates diverse anomalies
• Anomaly Prompt Pool enables robust anomaly detection