Anomaly Prediction: A Novel Approach with Explicit Delay and Horizon

TL;DR

This paper presents a new method for time series anomaly prediction that explicitly incorporates delay and horizon information, improving the timeliness and accuracy of anomaly detection.

Contribution

It introduces a novel approach that directly models temporal dynamics in anomaly prediction and provides a new dataset for evaluation.

Findings

Outperforms existing methods in timely anomaly detection

Provides more accurate predictions by considering delay and horizon

Sets a new benchmark for future anomaly prediction research

Abstract

Anomaly detection in time series data is a critical challenge across various domains. Traditional methods typically focus on identifying anomalies in immediate subsequent steps, often underestimating the significance of temporal dynamics such as delay time and horizons of anomalies, which generally require extensive post-analysis. This paper introduces a novel approach for time series anomaly prediction, incorporating temporal information directly into the prediction results. We propose a new dataset specifically designed to evaluate this approach and conduct comprehensive experiments using several state-of-the-art methods. Our results demonstrate the efficacy of our approach in providing timely and accurate anomaly predictions, setting a new benchmark for future research in this field.