Quantum Reservoir Computing for Credit Card Default Prediction on a Neutral Atom Platform

TL;DR

This work tackles credit-card default prediction using a hybrid quantum-classical pipeline that embeds a Quantum Reservoir Computing (QRC) layer on QuEra's 256-qubit neutral-atom platform (Aquila). It systematically compares two data encodings (position and detuning) and benchmarks against a fully classical Deep Neural Network (DNN) and a noiseless QRC emulation, while evaluating the impact of hardware noise. Emulation results show that, in a noiseless setting, QRC can achieve competitive performance relative to the DNN, but real hardware noise degrades accuracy, highlighting challenges for NISQ-era quantum methods. The study demonstrates the feasibility and potential scalability of QRC for real-world tasks on neutral-atom platforms and outlines directions toward gate-based and digital QRC to broaden applicability.

Abstract

In this paper, we define and benchmark a hybrid quantum-classical machine learning pipeline by performing a binary classification task applied to a real-world financial use case. Specifically, we implement a Quantum Reservoir Computing (QRC) layer within a classical routine that includes data preprocessing and binary classification. The reservoir layer has been executed on QuEra's Aquila, a 256-qubit neutral atom simulator, using two different types of encoding: position and local detuning. In the former case, classical data are encoded into the relative distance between atoms; in the latter, into pulse amplitudes. The developed pipeline is applied to predict credit card defaults using a public dataset and a wide variety of traditional classifiers. The results are compared with a fully-classical pipeline including a Deep Neural Network (DNN) model. Additionally, the impact of hardware noise on classification performance is evaluated by comparing the results obtained using Aquila within the classification workflow with those obtained using a classical, noiseless emulation of the quantum system. The results indicate that the noiseless emulation achieves competitive performance with the fully-classical pipeline, while noise significantly degrades overall performance. Although the results for this specific use case are comparable to those of the classical benchmark, the flexibility and scalability of QRC highlight strong potential for a wide range of applications.

Figures (12)

• Figure 1: High-level view of the hybrid quantum-classical classification pipeline.
• Figure 2: PCA explained variance, computed on the CARDS_30000 dataset.
• Figure 3: Features aggregation on the CARDS_30000 dataset.
• Figure 4: Example pulse sequence for the (a) position encoding and (b) detuning encoding. In the latter case, we considered a short 5 qubit array for the sake of readability. The relative local detuning waveforms are plotted using different colors.
• Figure 5: F1-score as a function on the number of Hamiltonian simulations. Dotted lines refer to classification scores on the noiseless statevector emulation of the QRC procedure.