Challenges
Datasets
Workspaces
Papers
Discussions
Leaderboard
Log inSign up
Challenges
Datasets
Workspaces
Papers
Discussions
Leaderboard
Blog
Job Board
Q3AS

© 2026 Aqora Quantum S.A.S.

TermsPrivacyLegal Notice

arXiv:2610.12148

Large-Scale Benchmarking of Quantum Neural Network Configurations for Financial Time Series Forecasting

Jack Waller, Xing Liang, Dimitrios Makris, Rajagopal Nilavalan

cs.LGquant-phSubmitted Oct 8, 2026• Announced Oct 9, 2026• 0 citations
arXivHTMLPDF

Abstract

Quantum machine learning, and quantum neural networks (QNNs) in particular, are advancing fields with growing potential. Although systematic comparisons of QNN configurations have been explored primarily for classification tasks, comparatively little attention has been given to regression problems, particularly financial time series forecasting. This study presents a large-scale systematic comparative evaluation of QNN component configurations for financial time series forecasting, using the GBP/USD spot exchange rate as a case study. A grid search across encoding methods, ansatz designs, qubit counts, layer depths, and cost functions yields 1,368 distinct model configurations, each evaluated in terms of prediction accuracy, computational cost, and convergence behaviour. The results reveal unique insights into how the choice of methods influences performance, such as that gate selection and arrangement are more critical to model success than raw parameter count, and that entanglement is a system-level property of the full circuit rather than solely at the ansatz level. The best-performing QNN configuration achieves an $R^2$ score of 0.985, outperforming a classical BiLSTM baseline. Additionally, the impact of real quantum hardware noise is assessed through execution on the IQM Emerald device, revealing that gate errors and decoherence represent a significant barrier to practical deployment, with gate selection and circuit depth identified as key determinants of hardware noise resilience. Overall, the findings provide practical architectural guidance for QNN design and establish a baseline characterisation of QNN noise sensitivity on near-term quantum devices.

AI Summary

The paper examines how quantum neural network (QNN) architecture choices affect financial time-series regression, using daily GBP/USD exchange rates as a case study. It evaluates 1,368 configurations spanning three encodings, twelve ansätze, 4–12 qubits, up to eight layers, and MSE or fidelity-based losses. Each configuration is trained in noiseless simulation with five random initialisations. The 5,000-point dataset is split chronologically into 3,000 training, 500 validation, and 1,500 test samples. The best individual run uses angle encoding, four qubits, eight layers, and an MSE loss, achieving test $R^2=0.98495$ and MSE $5.6693\times10^{-5}$. Reported best-run BiLSTM baselines achieve $R^2=0.9529$ under restricted input conditions and $0.9805$ with longer, overlapping windows. Amplitude encoding gives the strongest mean performance across configurations, although its mean $R^2$ remains negative. Comparisons indicate that gate arrangement matters beyond parameter count, additional layers generally improve accuracy, and entangling encodings can partly compensate for limited ansatz entanglement. Selected simulator-trained circuits are also evaluated during inference on IQM Emerald using 1,024 shots. The reported mean $R^2$ reduction is approximately 1.25 on hardware, versus 0.06 in an SV1 comparison attributed to readout noise; the best hardware result is $R^2=0.77$. Shallower circuits retain more accuracy, while non-native gate decompositions increase implementation costs. Stated limitations include computational restrictions on circuit size, single-run hardware evaluations, substantial hardware-noise degradation, and unresolved explanations involving barren plateaus. Generalisation to other datasets and architectures remains unestablished, and a controlled quantum-advantage study is outside scope.

Little sign of AI-generated textOverclaimsIncrementalMissing comparisonPossible error

Central claim may not hold: The claimed QNN superiority relies on the highest individual test score found across a large configuration-and-initialisation search, rather than demonstrated superiority of a validation-selected model on an untouched test set. The winning QNN and the constrained BiLSTM use different window lengths, and identical forecast timestamps are not established, undermining the claim of equivalent data conditions. The architecture rankings establish that parameter count alone is insufficient to predict performance, but do not establish that gate selection and arrangement are more critical than parameter count. The entanglement comparisons confound entanglement with access to input features and other architectural changes, so they do not establish entanglement as a necessary forecasting resource.

Written by gpt-6.1-sol from the paper's full text. Automated: it can be wrong.

Related papers

Quantum neural networks for wind power prediction: a benchmark against classical machine learning models

Batuhan Hangun, Onder Eyecioglu, Mehar Ali +2 more

Abstract Quantum Machine Learning (QML) is an emerging field at the intersection of quantum computing and machine learning that aims to enhance classical learning methods by leveraging principles such as superposition and entanglement. However, skepticism remains regarding its practical advantages, particularly due to the limitations of noisy intermediate-scale quantum (NISQ) devices. This study addresses these concerns through a systematic evaluation of Quantum Neural Networks (QNNs), quantum-inspired counterparts of Artificial Neural Networks (ANNs). We construct and analyze 12 distinct QNN configurations by combining two quantum feature maps with six entanglement strategies for ansatz design. Experiments conducted on a wind energy dataset show that QNNs can achieve competitive or superior performance compared to classical baseline models, with the best-performing configuration (QNN-3) reaching an R 2 score of up to 0.94 when forecasting wind power output using four input features. In addition, we provide a detailed analysis of simulation time across different configurations, highlighting trade-offs between model complexity and computational cost. These findings demonstrate the potential of QNNs as viable models for predictive tasks and contribute to the ongoing evaluation of QML in real-world applications.

arXiv:2506.22845•Quantum Information Processing•Nov 9, 2026•3 citations

Advancing Computer Technology for Financial Forecasting: A Comparative Study of Quantum and Classical Machine Learning Approaches in Stock Price Prediction

Priya Ranjan Kumar, Piyush Ranjan

Stock market forecasting remains one of the most computationally demanding tasks in financial engineering, requiring sophisticated models capable of processing nonlinear patterns, high-frequency volatility, and large volumes of time-series data. Recent advancements in quantum computing offer the potential to surpass classical machine learning (ML) by leveraging principles such as superposition and entanglement to accelerate learning and optimization. This paper conducts a comprehensive comparison between quantum machine learning (QML) models and classical deep learning architectures for stock price prediction, emphasizing the technological improvements and optimization of computational methods. Our analysis integrates insights from prior studies, including the application of quantum-enhanced Gramian Angular Fields with CNNs [2], shallow parameterized quantum circuits for market indicators [4], and hybrid quantum-classical algorithms tailored to finance [1]. Experimental evaluation (using IBM Qiskit's quantum simulators and real hardware) demonstrates competitive performance of quantum neural networks (QNNs) against state-of-the-art recurrent neural networks (RNNs) and long short-term memory (LSTM) architectures [3]. Across AAPL/MSFT and short horizons, compact QNNs match strong LSTM baselines while using an order of magnitude fewer parameters, and—critically—transfer from calibrated simulators to IBM hardware with marginal degradation after mitigation. This device-aware training/evaluation loop exemplifies a deployable path for financial QML under realistic noise and resource constraints and motivates standardized, time-series-aware testing for the community. Results highlight the engineering value of quantum acceleration in feature encoding, the research novelty of hybrid ensemble strategies, and the future scope of benchmarking across leading quantum computing machines such as IBM, Google Sycamore, Rigetti, IonQ, and Xanadu.

International Conference on Big Data Economy and Information Management (BDEIM)•Dec 19, 2025•1 citation

Benchmarking Encoding Families in Quantum Neural Networks Under Fixed Circuit Area for Frequency Spectrum and Trainability

Martyna Czuba, Patrick Holzer, Hein Zay Yar Oo

Quantum Neural Networks (QNNs) offer a promising framework for integrating quantum computing principles into machine learning, yet their practical capabilities and limitations remain insufficiently studied. In this work, we systematically investigate the trainability and approximation properties of QNNs by benchmarking diverse circuit architectures and encoding strategies across synthetic and real-world datasets. We analyze several ansätze, including Hamming, binary, exponential, ternary, turnpike and Golomb, by evaluating their ability to learn synthetic data modeled as random finite Fourier series. To assess real-world applicability, we further evaluate QNNs on two time-series classification tasks: a Fischertechnik pneumatic leak detection dataset and the publicly available NASA bearing fault dataset. Our experiments show that while broader frequency spectra can theoretically enhance expressivity, practical trainability is strongly influenced by architectural factors such as qubit count and circuit depth. Notably, we find that QNNs perform best when the frequency spectrum is tailored to the target function's complexity but remains as compact as possible. Moreover, architectures with identical frequency spectra can differ in trainability, with configurations using more qubits and fewer layers generally performing better, except in the single-layer case. These findings provide guidelines for selecting QNN ansätze and offer new insights into the interplay between expressivity and trainability in quantum machine learning.

quant-pharXiv:2603.27671•Mar 31, 2026•1 citation

Comparative Analysis of QNN Architectures for Wind Power Prediction: Feature Maps and Ansatz Configurations

Batuhan Hangun, Emine Akpinar, Oguz Altun +1 more

Quantum Machine Learning (QML) is an emerging field at the intersection of quantum computing and machine learning, aiming to enhance classical machine learning methods by leveraging quantum mechanics principles such as entanglement and superposition. However, skepticism persists regarding the practical advantages of QML, mainly due to the current limitations of noisy intermediate-scale quantum (NISQ) devices. This study addresses these concerns by extensively assessing Quantum Neural Networks (QNNs)-quantum-inspired counterparts of Artificial Neural Networks (ANNs), demonstrating their effectiveness compared to classical methods. We systematically construct and evaluate twelve distinct QNN configurations, utilizing two unique quantum feature maps combined with six different entanglement strategies for ansatz design. Experiments conducted on a wind energy dataset reveal that QNNs employing the $\mathbf{Z}$ feature map achieve up to $93 \%$ prediction accuracy when forecasting wind power output using only four input parameters. Our findings show that QNNs outperform classical methods in predictive tasks, underscoring the potential of QML in real-world applications.

arXiv:2506.14795•IEEE Computer Society Annual Symposium on VLSI•Jul 6, 2025•6 citations

Quantum Machine Learning in Finance: Time Series Forecasting

Dimitrios Emmanoulopoulos, Sofija Dimoska

We explore the efficacy of the novel use of parametrised quantum circuits (PQCs) as quantum neural networks (QNNs) for forecasting time series signals with simulated quantum forward propagation. The temporal signals consist of several sinusoidal components (deterministic signal), blended together with trends and additive noise. The performance of the PQCs is compared against that of classical bidirectional long short-term memory (BiLSTM) neural networks. Our results show that for time series signals consisting of small amplitude noise variations (up to 40 per cent of the amplitude of the deterministic signal) PQCs, with only a few parameters, perform similar to classical BiLSTM networks, with thousands of parameters, and outperform them for signals with higher amplitude noise variations. Thus, QNNs can be used effectively to model time series having, at the same time, the significant advantage of being trained significantly faster than a classical machine learning model in a quantum computer.

arXiv:2202.00599•Feb 1, 2022•79 citations

Quantum and quantum-inspired neural networks for time series forecasting: A systematic review with agricultural applications

Sujith Arokia Swamy B, Raj Shekar M, Bhavana Kabber +1 more

Quantum machine learning (QML) has emerged as a promising paradigm for time series forecasting, offering potential advantages in expressivity, parameter efficiency, and computational scaling through quantum mechanical principles such as superposition, entanglement, and interference. This systematic review synthesizes 112 primary studies published between 2020 and 2026, providing the first comprehensive assessment of quantum and quantum-inspired neural networks for time series forecasting with a dedicated focus on agricultural applications. We develop a taxonomy distinguishing fully quantum models (Quantum RNNs, Quantum LSTMs), hybrid quantum-classical architectures (QLSTM, Q-Informer, QKAN-LSTM), quantum kernel methods (QSVM, QK-LSTM), quantum reservoir computing (QRC), and quantum-inspired classical algorithms. Our synthesis finds that (i) Quantum LSTM (QLSTM) models consistently outperform classical LSTM baselines across weather, financial, and climate forecasting tasks; (ii) Quantum Reservoir Computing achieves competitive accuracy with significantly fewer trainable parameters, making it particularly suited to data-scarce agricultural price forecasting; (iii) hybrid quantum-classical frameworks for rice yield prediction achieve near-perfect accuracy (R2 = 0.99992); (iv) QKAN-LSTM achieves a 79% reduction in trainable parameters; (v) Q-Informer introduces learnable quantum attention scoring; and (vi) QRC applied to food price crisis prediction outperforms deep learning and statistical baselines. Despite these advances, we identify seven critical gaps: absence of standardized quantum benchmarking, hardware scalability limitations, noise resilience challenges, lack of reproducibility, limited cross-commodity validation, interpretability barriers, and the simulation-reality gap.

International Journal of Agriculture Extension and Social Development•Mar 1, 2026•0 citations
Quantum machine learning, and quantum neural networks (QNNs) in particular, are advancing fields with growing potential. Although systematic comparisons of QNN configurations have been explored primarily for classification tasks, comparatively little attention has been given to regression problems, particularly financial time series forecasting. This study presents a large-scale systematic comparative evaluation of QNN component configurations for financial time series forecasting, using the GBP/USD spot exchange rate as a case study. A grid search across encoding methods, ansatz designs, qubit counts, layer depths, and cost functions yields 1,368 distinct model configurations, each evaluated in terms of prediction accuracy, computational cost, and convergence behaviour. The results reveal unique insights into how the choice of methods influences performance, such as that gate selection and arrangement are more critical to model success than raw parameter count, and that entanglement is a system-level property of the full circuit rather than solely at the ansatz level. The best-performing QNN configuration achieves an R2R^2R2 score of 0.985, outperforming a classical BiLSTM baseline. Additionally, the impact of real quantum hardware noise is assessed through execution on the IQM Emerald device, revealing that gate errors and decoherence represent a significant barrier to practical deployment, with gate selection and circuit depth identified as key determinants of hardware noise resilience. Overall, the findings provide practical architectural guidance for QNN design and establish a baseline characterisation of QNN noise sensitivity on near-term quantum devices.
The paper examines how quantum neural network (QNN) architecture choices affect financial time-series regression, using daily GBP/USD exchange rates as a case study. It evaluates 1,368 configurations spanning three encodings, twelve ansätze, 4–12 qubits, up to eight layers, and MSE or fidelity-based losses. Each configuration is trained in noiseless simulation with five random initialisations. The 5,000-point dataset is split chronologically into 3,000 training, 500 validation, and 1,500 test samples.
The best individual run uses angle encoding, four qubits, eight layers, and an MSE loss, achieving test R2=0.98495R^2=0.98495R2=0.98495 and MSE 5.6693×10−55.6693\times10^{-5}5.6693×10−5. Reported best-run BiLSTM baselines achieve R2=0.9529R^2=0.9529R2=0.9529 under restricted input conditions and 0.98050.98050.9805 with longer, overlapping windows. Amplitude encoding gives the strongest mean performance across configurations, although its mean R2R^2R2 remains negative. Comparisons indicate that gate arrangement matters beyond parameter count, additional layers generally improve accuracy, and entangling encodings can partly compensate for limited ansatz entanglement.
Selected simulator-trained circuits are also evaluated during inference on IQM Emerald using 1,024 shots. The reported mean R2R^2R2 reduction is approximately 1.25 on hardware, versus 0.06 in an SV1 comparison attributed to readout noise; the best hardware result is R2=0.77R^2=0.77R2=0.77. Shallower circuits retain more accuracy, while non-native gate decompositions increase implementation costs.
Stated limitations include computational restrictions on circuit size, single-run hardware evaluations, substantial hardware-noise degradation, and unresolved explanations involving barren plateaus. Generalisation to other datasets and architectures remains unestablished, and a controlled quantum-advantage study is outside scope.
Abstract Quantum Machine Learning (QML) is an emerging field at the intersection of quantum computing and machine learning that aims to enhance classical learning methods by leveraging principles such as superposition and entanglement. However, skepticism remains regarding its practical advantages, particularly due to the limitations of noisy intermediate-scale quantum (NISQ) devices. This study addresses these concerns through a systematic evaluation of Quantum Neural Networks (QNNs), quantum-inspired counterparts of Artificial Neural Networks (ANNs). We construct and analyze 12 distinct QNN configurations by combining two quantum feature maps with six entanglement strategies for ansatz design. Experiments conducted on a wind energy dataset show that QNNs can achieve competitive or superior performance compared to classical baseline models, with the best-performing configuration (QNN-3) reaching an R 2 score of up to 0.94 when forecasting wind power output using four input features. In addition, we provide a detailed analysis of simulation time across different configurations, highlighting trade-offs between model complexity and computational cost. These findings demonstrate the potential of QNNs as viable models for predictive tasks and contribute to the ongoing evaluation of QML in real-world applications.
Stock market forecasting remains one of the most computationally demanding tasks in financial engineering, requiring sophisticated models capable of processing nonlinear patterns, high-frequency volatility, and large volumes of time-series data. Recent advancements in quantum computing offer the potential to surpass classical machine learning (ML) by leveraging principles such as superposition and entanglement to accelerate learning and optimization. This paper conducts a comprehensive comparison between quantum machine learning (QML) models and classical deep learning architectures for stock price prediction, emphasizing the technological improvements and optimization of computational methods. Our analysis integrates insights from prior studies, including the application of quantum-enhanced Gramian Angular Fields with CNNs [2], shallow parameterized quantum circuits for market indicators [4], and hybrid quantum-classical algorithms tailored to finance [1]. Experimental evaluation (using IBM Qiskit's quantum simulators and real hardware) demonstrates competitive performance of quantum neural networks (QNNs) against state-of-the-art recurrent neural networks (RNNs) and long short-term memory (LSTM) architectures [3]. Across AAPL/MSFT and short horizons, compact QNNs match strong LSTM baselines while using an order of magnitude fewer parameters, and—critically—transfer from calibrated simulators to IBM hardware with marginal degradation after mitigation. This device-aware training/evaluation loop exemplifies a deployable path for financial QML under realistic noise and resource constraints and motivates standardized, time-series-aware testing for the community. Results highlight the engineering value of quantum acceleration in feature encoding, the research novelty of hybrid ensemble strategies, and the future scope of benchmarking across leading quantum computing machines such as IBM, Google Sycamore, Rigetti, IonQ, and Xanadu.
Quantum Neural Networks (QNNs) offer a promising framework for integrating quantum computing principles into machine learning, yet their practical capabilities and limitations remain insufficiently studied. In this work, we systematically investigate the trainability and approximation properties of QNNs by benchmarking diverse circuit architectures and encoding strategies across synthetic and real-world datasets. We analyze several ansätze, including Hamming, binary, exponential, ternary, turnpike and Golomb, by evaluating their ability to learn synthetic data modeled as random finite Fourier series. To assess real-world applicability, we further evaluate QNNs on two time-series classification tasks: a Fischertechnik pneumatic leak detection dataset and the publicly available NASA bearing fault dataset. Our experiments show that while broader frequency spectra can theoretically enhance expressivity, practical trainability is strongly influenced by architectural factors such as qubit count and circuit depth. Notably, we find that QNNs perform best when the frequency spectrum is tailored to the target function's complexity but remains as compact as possible. Moreover, architectures with identical frequency spectra can differ in trainability, with configurations using more qubits and fewer layers generally performing better, except in the single-layer case. These findings provide guidelines for selecting QNN ansätze and offer new insights into the interplay between expressivity and trainability in quantum machine learning.
Quantum Machine Learning (QML) is an emerging field at the intersection of quantum computing and machine learning, aiming to enhance classical machine learning methods by leveraging quantum mechanics principles such as entanglement and superposition. However, skepticism persists regarding the practical advantages of QML, mainly due to the current limitations of noisy intermediate-scale quantum (NISQ) devices. This study addresses these concerns by extensively assessing Quantum Neural Networks (QNNs)-quantum-inspired counterparts of Artificial Neural Networks (ANNs), demonstrating their effectiveness compared to classical methods. We systematically construct and evaluate twelve distinct QNN configurations, utilizing two unique quantum feature maps combined with six different entanglement strategies for ansatz design. Experiments conducted on a wind energy dataset reveal that QNNs employing the Z\mathbf{Z}Z feature map achieve up to 93%93 \%93% prediction accuracy when forecasting wind power output using only four input parameters. Our findings show that QNNs outperform classical methods in predictive tasks, underscoring the potential of QML in real-world applications.
We explore the efficacy of the novel use of parametrised quantum circuits (PQCs) as quantum neural networks (QNNs) for forecasting time series signals with simulated quantum forward propagation. The temporal signals consist of several sinusoidal components (deterministic signal), blended together with trends and additive noise. The performance of the PQCs is compared against that of classical bidirectional long short-term memory (BiLSTM) neural networks. Our results show that for time series signals consisting of small amplitude noise variations (up to 40 per cent of the amplitude of the deterministic signal) PQCs, with only a few parameters, perform similar to classical BiLSTM networks, with thousands of parameters, and outperform them for signals with higher amplitude noise variations. Thus, QNNs can be used effectively to model time series having, at the same time, the significant advantage of being trained significantly faster than a classical machine learning model in a quantum computer.
Quantum machine learning (QML) has emerged as a promising paradigm for time series forecasting, offering potential advantages in expressivity, parameter efficiency, and computational scaling through quantum mechanical principles such as superposition, entanglement, and interference. This systematic review synthesizes 112 primary studies published between 2020 and 2026, providing the first comprehensive assessment of quantum and quantum-inspired neural networks for time series forecasting with a dedicated focus on agricultural applications. We develop a taxonomy distinguishing fully quantum models (Quantum RNNs, Quantum LSTMs), hybrid quantum-classical architectures (QLSTM, Q-Informer, QKAN-LSTM), quantum kernel methods (QSVM, QK-LSTM), quantum reservoir computing (QRC), and quantum-inspired classical algorithms. Our synthesis finds that (i) Quantum LSTM (QLSTM) models consistently outperform classical LSTM baselines across weather, financial, and climate forecasting tasks; (ii) Quantum Reservoir Computing achieves competitive accuracy with significantly fewer trainable parameters, making it particularly suited to data-scarce agricultural price forecasting; (iii) hybrid quantum-classical frameworks for rice yield prediction achieve near-perfect accuracy (R2 = 0.99992); (iv) QKAN-LSTM achieves a 79% reduction in trainable parameters; (v) Q-Informer introduces learnable quantum attention scoring; and (vi) QRC applied to food price crisis prediction outperforms deep learning and statistical baselines. Despite these advances, we identify seven critical gaps: absence of standardized quantum benchmarking, hardware scalability limitations, noise resilience challenges, lack of reproducibility, limited cross-commodity validation, interpretability barriers, and the simulation-reality gap.