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:2510.21168 · The Journal of Supercomputing

Quantum-enhanced architectures for multivariate time-series forecasting

Sandra Ranilla-Cortina, Diego A. Aranda, Jorge Ballesteros, Jesús Bonilla, Nerea Monrio, Elías F. Combarro

Published Feb 12, 2026• 4 citations
arXivHTMLPDF

Abstract

Abstract In this paper, we address the challenge of multivariate time-series forecasting through quantum-enhanced machine learning architectures. We propose adaptation strategies that extend variational quantum circuit models (VQC), traditionally constrained to univariate data, toward the multivariate setting, exploring both purely quantum and hybrid quantum-classical formulations. First, we extend and benchmark several VQC-based and hybrid models to systematically evaluate their ability to capture cross-variable dependencies. Building on these foundations, we introduce the iQTransformer, a novel quantum transformer architecture that integrates a quantum self-attention mechanism within the iTransformer framework, enabling a quantum-native representation of inter-variable relationships. Finally, we present a comprehensive empirical evaluation on both synthetic and real-world datasets, demonstrating that quantum-enhanced models can achieve competitive or superior forecasting accuracy with fewer trainable parameters and faster convergence than state-of-the-art classical and quantum baselines. These findings highlight the potential of quantum-enhanced architectures as efficient and scalable tools for advancing multivariate time-series forecasting.

DOI
10.1007/s11227-026-08295-x

Related papers

A Quantum-Classical Hybrid Framework for Multivariate Time-Series Forecasting Complexity-Fidelity Trade-offs and Limitations

Sanjay Chakraborty, Fredrik Heintz

This paper presents a unified quantum-classical hybrid framework for multi-horizon time-series forecasting, introducing two model variants Quantum Reservoir Forecaster (QRC-F) and Variational Quantum Forecaster (VQF-F). The proposed framework investigates the complexity-fidelity trade-off of quantum forecasting under near-term NISQ hardware constraints. Continuous time-series signals are transformed into binary representations through uniform quantization and encoded into quantum states using angle encoding with parameterized RY rotation gates. Cross-channel entanglement layers capture dependencies among multiple variables. QRC-F utilizes a fixed random unitary quantum reservoir for stable, gradient-free temporal feature extraction, whereas VQF-F employs a trainable variational quantum circuit optimized through the parameter-shift rule to learn temporal and inter-variable patterns from Pauli expectation values. Both models replace computationally expensive quadratic self-attention with efficient linear transformations, reducing parameter complexity. A shared MIMO-based multi-horizon prediction head simultaneously generates forecasts across multiple horizons, avoiding error accumulation in recursive forecasting. Experimental evaluations on benchmark datasets, including ETTh1, ETTh2, ETTm1, ETTm2, Weather, electricity, and exchange-rate, demonstrate that VQF-F achieves superior training stability and parameter efficiency, while QRC-F provides enhanced robustness and circuit fidelity under quantum noise. The results establish a practical quantum-native forecasting framework with strong potential for deployment on near-term NISQ devices.

arXiv:2607.16358•Jul 17, 2026•0 citations

Optimizing Hybrid Quantum-Classical Models Using Parameterized Quantum Circuits for Time-Series Forecasting

Harshraj Bhoite

Time-series forecasting is vital across sectors such as finance, energy, and environmental science, where accurate future predictions drive informed decision-making. Traditional statistical methods and deep learning models like LSTM and Transformers, while effective, often struggle with high-dimensional data and long-term dependencies. In this paper, we propose a hybrid quantum-classical model that utilizes Parameterized Quantum Circuits (PQCs) to capture complex temporal patterns in multivariate time-series data. Our architecture integrates a classical encoder, a quantum variational processor, and a classical decoder, trained end-to-end using gradient-based optimization. Experiments conducted on benchmark datasets—electricity load, stock prices, and weather forecasting—demonstrate that the hybrid model consistently outperforms classical baselines in terms of Mean Squared Error (MSE), Mean Absolute Error (MAE), and R² score. Robustness analysis confirms the model’s resilience to moderate quantum noise, while an ablation study highlights the performance gain from quantum components. This work showcases the potential of hybrid quantum-classical approaches on Noisy Intermediate-Scale Quantum (NISQ) devices and lays a foundation for scalable, real-world quantum machine learning applications.

•Jul 19, 2025•0 citations

Integrating Quantum-Classical Attention in Patch Transformers for Enhanced Time Series Forecasting

Sanjay Chakraborty, Fredrik Heintz

QCAAPatchTF is a quantum attention network integrated with an advanced patch-based transformer, designed for multivariate time series forecasting, classification, and anomaly detection. Leveraging quantum superpositions, entanglement, and variational quantum eigensolver principles, the model introduces a quantum-classical hybrid self-attention mechanism to capture multivariate correlations across time points. For multivariate long-term time series, the quantum self-attention mechanism can reduce computational complexity while maintaining temporal relationships. It then applies the quantum-classical hybrid self-attention mechanism alongside a feed-forward network in the encoder stage of the advanced patch-based transformer. While the feed-forward network learns nonlinear representations for each variable frame, the quantum self-attention mechanism processes individual series to enhance multivariate relationships. The advanced patch-based transformer computes the optimized patch length by dividing the sequence length into a fixed number of patches instead of using an arbitrary set of values. The stride is then set to half of the patch length to ensure efficient overlapping representations while maintaining temporal continuity. QCAAPatchTF achieves state-of-the-art performance in both long-term and short-term forecasting, classification, and anomaly detection tasks, demonstrating state-of-the-art accuracy and efficiency on complex real-world datasets.

arXiv:2504.00068•Mar 31, 2025•9 citations

High-Dimensional Time Series Forecasting Models: A Quantum Adaptive Learning Approach

Jincheng Zhang

This paper explores the application of quantum self-adaptive learning to high-dimensional time series forecasting models, leveraging the unique properties of quantum computing to enhance prediction accuracy and efficiency, particularly in scenarios involving large datasets and complex feature representations. We propose a novel "Quantum Adaptive Adjustment" mechanism that dynamically adjusts the learning process based on the characteristics of the time series data, leading to improved model performance. The research focuses on mitigating the limitations of traditional machine learning algorithms in handling high dimensionality and complex patterns, presenting a promising approach for improved forecasting capabilities. The paper details the implementation of the quantum self-adaptive learning process, including the introduction of the adaptive adjustment mechanism and a comprehensive evaluation of its effectiveness through simulations and a benchmark dataset. We conclude with a discussion of the potential impact of this approach on various real-world time series forecasting tasks.

•Aug 31, 2026•0 citations

Hybrid Encoding-based Quantum Self Attention for Financial Time Series Analysis

S Lokes, Suresh Reddy, Samuel Yen Chi Chen

Self-attention mechanisms, central to Transformer architectures, have become foundational in the development of large language models (LLMs) and various advanced machine learning systems. These mechanisms are pivotal for effectively capturing complex data dependencies and relationships, which is crucial for tasks such as natural language understanding and generation. However, as dimensionality increases, self-attention mechanisms face significant challenges related to computational efficiency and scalability. This paper introduces an encoding-based quantum self-attention mechanism designed to address these issues by embedding classical data into quantum states. This approach facilitates more efficient computation and reduces model complexity. To further enhance performance for real-world applications, particularly in financial time series forecasting, we propose a hybrid model that integrates Long Short-Term Memory (LSTM) networks with quantum self-attention mechanism. Given the constraints of the Noisy Intermediate-Scale Quantum (NISQ) era, this hybrid approach represents a plausible solution, leveraging the strengths of both classical and quantum methods and focusing on achieving faster convergence. Experimental results demonstrate that our approach converges significantly quicker than traditional models, showcasing the advantages of integrating quantum techniques with classical machine learning for practical applications.

IEEE International Conference on Acoustics, Speech, and Signal Processing Workshops (ICASSPW)•Apr 6, 2025•1 citation

ADVANCING FINANCIAL PREDICTION THROUGH QUANTUM MACHINE LEARNING

Ananya (Ph.D. Candidate) Patel

The growing complexity, interdependencies, and rapid fluctuations inherent in modern financial markets create substantial challenges for accurate forecasting, portfolio optimization, and risk management. Conventional machine learning techniques, while powerful, often face limitations in capturing nonlinear relationships and processing high-dimensional datasets efficiently. Quantum machine learning (QML) has emerged as a promising paradigm that leverages quantum computing principles to enhance predictive modeling in finance. This study presents a comprehensive investigation into the application of QML methods—including variational quantum circuits, quantum kernel estimation, and quantum-enhanced support vector machines—for financial time-series prediction and asset price classification. We propose a hybrid quantum-classical framework that integrates quantum feature mapping with classical optimizers to improve model expressiveness and convergence. Empirical experiments are conducted using historical stock market data and synthetic datasets to benchmark QML approaches against established classical models such as long short-term memory networks and gradient boosting machines. The results demonstrate that QML techniques can achieve superior prediction accuracy and lower computational latency under certain data regimes, particularly when dealing with small-to-medium-sized datasets and high feature correlations. Additionally, the study examines scalability considerations, hardware constraints of near-term quantum devices, and the interpretability of quantum model outputs in financial decision-making contexts. The findings underscore the transformative potential of quantum machine learning as an innovative tool for advancing predictive analytics in finance and provide practical insights into how financial institutions can begin integrating QML capabilities into their workflows.

International Journal of Intelligent Data and Machine Learning•Feb 1, 2025•2 citations
Abstract In this paper, we address the challenge of multivariate time-series forecasting through quantum-enhanced machine learning architectures. We propose adaptation strategies that extend variational quantum circuit models (VQC), traditionally constrained to univariate data, toward the multivariate setting, exploring both purely quantum and hybrid quantum-classical formulations. First, we extend and benchmark several VQC-based and hybrid models to systematically evaluate their ability to capture cross-variable dependencies. Building on these foundations, we introduce the iQTransformer, a novel quantum transformer architecture that integrates a quantum self-attention mechanism within the iTransformer framework, enabling a quantum-native representation of inter-variable relationships. Finally, we present a comprehensive empirical evaluation on both synthetic and real-world datasets, demonstrating that quantum-enhanced models can achieve competitive or superior forecasting accuracy with fewer trainable parameters and faster convergence than state-of-the-art classical and quantum baselines. These findings highlight the potential of quantum-enhanced architectures as efficient and scalable tools for advancing multivariate time-series forecasting.
This paper presents a unified quantum-classical hybrid framework for multi-horizon time-series forecasting, introducing two model variants Quantum Reservoir Forecaster (QRC-F) and Variational Quantum Forecaster (VQF-F). The proposed framework investigates the complexity-fidelity trade-off of quantum forecasting under near-term NISQ hardware constraints. Continuous time-series signals are transformed into binary representations through uniform quantization and encoded into quantum states using angle encoding with parameterized RY rotation gates. Cross-channel entanglement layers capture dependencies among multiple variables. QRC-F utilizes a fixed random unitary quantum reservoir for stable, gradient-free temporal feature extraction, whereas VQF-F employs a trainable variational quantum circuit optimized through the parameter-shift rule to learn temporal and inter-variable patterns from Pauli expectation values. Both models replace computationally expensive quadratic self-attention with efficient linear transformations, reducing parameter complexity. A shared MIMO-based multi-horizon prediction head simultaneously generates forecasts across multiple horizons, avoiding error accumulation in recursive forecasting. Experimental evaluations on benchmark datasets, including ETTh1, ETTh2, ETTm1, ETTm2, Weather, electricity, and exchange-rate, demonstrate that VQF-F achieves superior training stability and parameter efficiency, while QRC-F provides enhanced robustness and circuit fidelity under quantum noise. The results establish a practical quantum-native forecasting framework with strong potential for deployment on near-term NISQ devices.
Time-series forecasting is vital across sectors such as finance, energy, and environmental science, where accurate future predictions drive informed decision-making. Traditional statistical methods and deep learning models like LSTM and Transformers, while effective, often struggle with high-dimensional data and long-term dependencies. In this paper, we propose a hybrid quantum-classical model that utilizes Parameterized Quantum Circuits (PQCs) to capture complex temporal patterns in multivariate time-series data. Our architecture integrates a classical encoder, a quantum variational processor, and a classical decoder, trained end-to-end using gradient-based optimization. Experiments conducted on benchmark datasets—electricity load, stock prices, and weather forecasting—demonstrate that the hybrid model consistently outperforms classical baselines in terms of Mean Squared Error (MSE), Mean Absolute Error (MAE), and R² score. Robustness analysis confirms the model’s resilience to moderate quantum noise, while an ablation study highlights the performance gain from quantum components. This work showcases the potential of hybrid quantum-classical approaches on Noisy Intermediate-Scale Quantum (NISQ) devices and lays a foundation for scalable, real-world quantum machine learning applications.
QCAAPatchTF is a quantum attention network integrated with an advanced patch-based transformer, designed for multivariate time series forecasting, classification, and anomaly detection. Leveraging quantum superpositions, entanglement, and variational quantum eigensolver principles, the model introduces a quantum-classical hybrid self-attention mechanism to capture multivariate correlations across time points. For multivariate long-term time series, the quantum self-attention mechanism can reduce computational complexity while maintaining temporal relationships. It then applies the quantum-classical hybrid self-attention mechanism alongside a feed-forward network in the encoder stage of the advanced patch-based transformer. While the feed-forward network learns nonlinear representations for each variable frame, the quantum self-attention mechanism processes individual series to enhance multivariate relationships. The advanced patch-based transformer computes the optimized patch length by dividing the sequence length into a fixed number of patches instead of using an arbitrary set of values. The stride is then set to half of the patch length to ensure efficient overlapping representations while maintaining temporal continuity. QCAAPatchTF achieves state-of-the-art performance in both long-term and short-term forecasting, classification, and anomaly detection tasks, demonstrating state-of-the-art accuracy and efficiency on complex real-world datasets.
This paper explores the application of quantum self-adaptive learning to high-dimensional time series forecasting models, leveraging the unique properties of quantum computing to enhance prediction accuracy and efficiency, particularly in scenarios involving large datasets and complex feature representations. We propose a novel "Quantum Adaptive Adjustment" mechanism that dynamically adjusts the learning process based on the characteristics of the time series data, leading to improved model performance. The research focuses on mitigating the limitations of traditional machine learning algorithms in handling high dimensionality and complex patterns, presenting a promising approach for improved forecasting capabilities. The paper details the implementation of the quantum self-adaptive learning process, including the introduction of the adaptive adjustment mechanism and a comprehensive evaluation of its effectiveness through simulations and a benchmark dataset. We conclude with a discussion of the potential impact of this approach on various real-world time series forecasting tasks.
Self-attention mechanisms, central to Transformer architectures, have become foundational in the development of large language models (LLMs) and various advanced machine learning systems. These mechanisms are pivotal for effectively capturing complex data dependencies and relationships, which is crucial for tasks such as natural language understanding and generation. However, as dimensionality increases, self-attention mechanisms face significant challenges related to computational efficiency and scalability. This paper introduces an encoding-based quantum self-attention mechanism designed to address these issues by embedding classical data into quantum states. This approach facilitates more efficient computation and reduces model complexity. To further enhance performance for real-world applications, particularly in financial time series forecasting, we propose a hybrid model that integrates Long Short-Term Memory (LSTM) networks with quantum self-attention mechanism. Given the constraints of the Noisy Intermediate-Scale Quantum (NISQ) era, this hybrid approach represents a plausible solution, leveraging the strengths of both classical and quantum methods and focusing on achieving faster convergence. Experimental results demonstrate that our approach converges significantly quicker than traditional models, showcasing the advantages of integrating quantum techniques with classical machine learning for practical applications.
The growing complexity, interdependencies, and rapid fluctuations inherent in modern financial markets create substantial challenges for accurate forecasting, portfolio optimization, and risk management. Conventional machine learning techniques, while powerful, often face limitations in capturing nonlinear relationships and processing high-dimensional datasets efficiently. Quantum machine learning (QML) has emerged as a promising paradigm that leverages quantum computing principles to enhance predictive modeling in finance. This study presents a comprehensive investigation into the application of QML methods—including variational quantum circuits, quantum kernel estimation, and quantum-enhanced support vector machines—for financial time-series prediction and asset price classification. We propose a hybrid quantum-classical framework that integrates quantum feature mapping with classical optimizers to improve model expressiveness and convergence. Empirical experiments are conducted using historical stock market data and synthetic datasets to benchmark QML approaches against established classical models such as long short-term memory networks and gradient boosting machines. The results demonstrate that QML techniques can achieve superior prediction accuracy and lower computational latency under certain data regimes, particularly when dealing with small-to-medium-sized datasets and high feature correlations. Additionally, the study examines scalability considerations, hardware constraints of near-term quantum devices, and the interpretability of quantum model outputs in financial decision-making contexts. The findings underscore the transformative potential of quantum machine learning as an innovative tool for advancing predictive analytics in finance and provide practical insights into how financial institutions can begin integrating QML capabilities into their workflows.