🤖 AI Summary
This study addresses the multi-step time series forecasting problem of ATM cash demand by introducing digital quantum reservoir computing to a real-world financial application for the first time. The approach employs a fixed-structure four-qubit quantum circuit, where temporal data are encoded via rotation angles, combined with partial measurement and qubit reset mechanisms, while only the classical ridge regression readout layer is trained. The work systematically evaluates the impact of circuit architecture, memory length, observables, and hardware backends on predictive performance and demonstrates feasibility on the IQM Spark quantum processor. Although the method does not outperform the classical Prophet model in terms of MAE and NMSE metrics, it achieves superior results under dynamic time warping (DTW), indicating a stronger capability to capture structural patterns in the time series.
📝 Abstract
We investigate a digital quantum reservoir computing (QRC) framework for multi-step forecasting of automated teller machine (ATM) cash demand time series on near-term quantum devices. The proposed approach uses parametrized four-qubit reservoirs with a fixed structure exploiting partial measurement and reset, where temporal data is encoded in rotation angles. Training is restricted to a classical Ridge-regression readout. We systematically analyze the impact of the circuit ansatzë, reservoir memory, measurement-derived observables, and the execution backend on the forecasting performance. Experiments are performed with noiseless simulation, noise-aware emulation, and a real IQM Spark quantum processor. Although the QRC models do not outperform the classical Prophet benchmark in terms of Mean Absolute Error and Normalized Mean Squared Error metrics, they achieve more competitive results in Dynamic Time Warping metric, indicating a partial ability to capture temporal structure. These findings provide an empirical assessment of digital QRC for realistic financial forecasting and highlight both its current limitations and its potential on near-term quantum hardware.