This work investigates how shallow NISQ-compatible quantum layers can improve temporal representation learning in real-world sequential data. We develop a QLSTM Seq2Seq autoencoder in which a depth-1 variational quantum circuit is embedded inside each recurrent gate, shaping the geometry of the learned latent manifold. Evaluated on fourteen rolling S&P500 windows from 2022–2025, the quantum-enhanced encoder produces smoother trajectories, clearer regime transitions, and more stable sector-coherent clusters than a classical LSTM baseline. These geometric properties support the use of a Radial Basis Function (RBF) kernel for downstream portfolio allocation, where both RBF-Graph and RBF-DivMom strategies consistently outperform their classical counterparts in risk-adjusted terms. Analysis across periods shows that compressed manifolds favour concentrated allocation, while dispersed manifolds favour diversification, demonstrating that latent geometry serves as a regime indicator. The results highlight a practical role for shallow hybrid quantum-classical layers in NISQ-era sequence modelling, offering a reproducible pathway for improving temporal embeddings in finance and other data-limited, noise-sensitive domains.
This work investigates how shallow NISQ-compatible quantum layers can improve temporal representation learning in real-world sequential data. We develop a QLSTM Seq2Seq autoencoder in which a depth-1 variational quantum circuit is embedded inside each recurrent gate, shaping the geometry of the learned latent manifold. Evaluated on fourteen rolling S&P500 windows from 2022–2025, the quantum-enhanced encoder produces smoother trajectories, clearer regime transitions, and more stable sector-coherent clusters than a classical LSTM baseline. These geometric properties support the use of a Radial Basis Function (RBF) kernel for downstream portfolio allocation, where both RBF-Graph and RBF-DivMom strategies consistently outperform their classical counterparts in risk-adjusted terms. Analysis across periods shows that compressed manifolds favour concentrated allocation, while dispersed manifolds favour diversification, demonstrating that latent geometry serves as a regime indicator. The results highlight a practical role for shallow hybrid quantum-classical layers in NISQ-era sequence modelling, offering a reproducible pathway for improving temporal embeddings in finance and other data-limited, noise-sensitive domains.
This study explores quantum and classical hybrid architectures for financial time-series fore casting, focusing on Quantum Long Short-Term Memory (QLSTM) networks and Quantum Reservoir Computing (QRC), using univariate and multivariate lag structures on real financial data. We assess how lag embeddings affect predictive accuracy and robustness. Data are en coded into quantum states via amplitude encoding, enabling efficient representation of normalized lagged observations under realistic qubit constraints. The recurrent dynamics of QLSTM and the reservoir of QRC are implemented as parameterized quantum circuits, while classical optimizers train the readout and, where applicable, variational circuit parameters. We benchmark quantum models against classical LSTM and reservoir computing using common error like metrics. Our results show that, with suitable lag selection and amplitude encoding, quantum-enhanced archi tectures match classical baselines in univariate settings and can modestly outperform them in multivariate regimes with correlated inputs, where expressive encodings are most beneficial.
Long short-term memory (LSTM) is a kind of recurrent neural networks (RNN) for sequence and temporal dependency data modeling and its effectiveness has been extensively established. In this work, we propose a hybrid quantum-classical model of LSTM, which we dub QLSTM. We demonstrate that the proposed model successfully learns several kinds of temporal data. In particular, we show that for certain testing cases, this quantum version of LSTM converges faster, or equivalently, reaches a better accuracy, than its classical counterpart. Due to the variational nature of our approach, the requirements on qubit counts and circuit depth are eased, and our work thus paves the way toward implementing machine learning algorithms for sequence modeling on noisy intermediate-scale quantum (NISQ) devices.
Long short-term memory (LSTM) is a kind of recurrent neural networks (RNN) for sequence and temporal dependency data modeling and its effectiveness has been extensively established. In this work, we propose a hybrid quantum-classical model of LSTM, which we dub QLSTM. We demonstrate that the proposed model successfully learns several kinds of temporal data. In particular, we show that for certain testing cases, this quantum version of LSTM converges faster, or equivalently, reaches a better accuracy, than its classical counterpart. Due to the variational nature of our approach, the requirements on qubit counts and circuit depth are eased, and our work thus paves the way toward implementing machine learning algorithms for sequence modeling such as natural language processing, speech recognition on noisy intermediate-scale quantum (NISQ) devices.
Hybrid Quantum Deep Learning (HQDL) models have emerged as a pragmatic bridge between the algorithmic richness of deep learning and the computational advantages of near-term quantum devices. Rather than seeking full quantum replacement of neural architectures, current research favours layered or modular integration-where variational quantum circuits, quantum kernels, or quantum-enhanced feature embeddings operate alongside classical neural networks. This convergence has yielded promising results in domains such as classification, generative modelling, molecular simulation, and combinatorial optimization. However, performance varies significantly depending on data encoding strategies, circuit expressivity, and training stability under hardware noise. This review synthesizes the taxonomy of existing HQDL architectures, evaluates their empirical benefits over purely classical baselines, and contextualizes their feasibility within current Noisy Intermediate-Scale Quantum (NISQ) constraints. Furthermore, it highlights reproducibility challenges, benchmarking inconsistencies, and open questions surrounding optimization landscapes and scalability. The analysis concludes that while HQDL remains in an early experimental phase, its trajectory is rapidly transitioning from proof-of-concept demonstrations toward targeted domain specialization in finance, materials discovery, and strategic decision-making.
Quantum Long Short-Term Memory (QLSTM) networks represent a promising direction in quantum machine learning but face challenges including parameter scaling, barren plateaus, and limitations of Noisy Intermediate-Scale Quantum (NISQ) hardware. This paper proposes the Tunable Ring Quantum LSTM (TRQLSTM) framework, integrating rotational encoding channels with a bidirectional ring Variational Quantum Circuit (VQC) architecture. Empirical evaluation on financial, weather, and electricity benchmarks demonstrates that TRQL-STM achieves a 98.7% parameter reduction over a classical LSTM while delivering a 95.1% MAE improvement on the Apple stock financial benchmark (AAPL). The bidirectional ring topology alone accounts for an 87.3% improvement over a standard QLSTM at identical parameter count. Expressibility is preserved at approximately 90% of a fully parameterised QLSTM, confirmed via KL divergence from the Haar random distribution. By combining optimised quantum gates, a bidirectional VQC layout, and multimodal encoding within a single circuit, TRQLSTM provides a practical pathway toward scalable quantum-classical sequential learning systems.
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.