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

Recently, forecasting future abnormal events has emerged as an important scenario to tackle realworld 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 AP, 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.

While previous work has focused on either forecasting future time series or detecting anomalies in existing data, no method has addressed the challenge of predicting when anomalies will occur in the future.To address this, we propose a unified model that combines time series forecasting with anomaly detection. Since anomalies are rare in time series data, we pretrain our model using a diverse set of learnable synthetic anomalies. This enables the model to recognize a wide range of abnormal patterns. As a result, our model demonstrates strong performance in accurately predicting the timing of anomalies across various real-world time series datasets.The key contribution of our work is that it opens up a new direction for time series research, introducing the first model that can predict when anomalies will occur.