Quantum Variational Rewinding for Time Series Anomaly Detection

Abstract

We explore a new quantum computing approach to time series anomaly detection (TAD). Our approach - Quantum Variational Rewinding (QVR) - trains a family of parameterized unitary time-devolution operators to cluster normal time series instances encoded within quantum states. Unseen time series are assigned an anomaly score based upon their distance from the cluster center, which, beyond a given threshold, classifies anomalous behaviour. We apply QVR to identify anomalous trading activity in cryptocurrency market data and blockchain. Finally, we study our algorithm on IBM’s Falcon r5.11H family of superconducting transmon QPUs, where anomaly score errors resulting from hardware noise are shown to be reducible by as much as 14% on average using advanced error mitigation techniques.