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:2408.03088 · IEEE International Conference on Quantum Computing and Engineering (QCE)

QADQN: Quantum Attention Deep Q-Network for Financial Market Prediction

Siddhant Dutta, Nouhaila Innan, Alberto Marchisio, Sadok Ben Yahia, Muhammad Shafique

Published Sep 15, 2024• 30 citations
arXivHTMLPDF

Abstract

Financial market prediction and optimal trading strategy development remain challenging due to market complexity and volatility. Our research in quantum finance and reinforcement learning for decision-making demonstrates the approach of quantum-classical hybrid algorithms to tackling real-world finan-cial challenges. In this respect, we corroborate the concept with rigorous backtesting and validate the framework's performance under realistic market conditions, by including fixed transaction cost per trade. This paper introduces a Quantum Attention Deep Q-Network (QADQN) approach to address these challenges through quantum-enhanced reinforcement learning. Our QADQN architecture uses a variational quantum circuit inside a traditional deep Q-learning framework to take advantage of possible quantum advantages in decision-making. We gauge the QADQN agent's performance on historical data from major market indices, including the S&P 500. We evaluate the agent's learning process by examining its reward accumulation and the effectiveness of its experience replay mechanism. Our empirical results demonstrate the QADQN's superior performance, achieving better risk-adjusted returns with Sortino ratios of 1.28 and 1.19 for non-overlapping and overlapping test periods respectively, indicating effective downside risk management.

DOI
10.1109/qce60285.2024.10303

Related papers

Hybrid Quantum – A Framework for High Frequency Stock Trading Using Reinforcement Learning

Anuj Mishra, Aviral Garg, Aditya Ghosh +2 more

This Paper shows information about the High Speed Stock Trading, In todays era the normal computers are struggling to identify and find the complex market patterns and strategies. So in order to solve this issue we built a new system that is a combination of quantum computing and classical computing in which Reinforcement Learning (a way for computers to learn with trial and error) is used with Quantum Machine Learning to make smarter trading decisions and strategies. Specially, we have used a quantum model (called a Variational Quantum classifier) as a part of Deep Q Network agent to help the system learning better trading strategies. Our goal is to use the superior representational power of quantum feature spaces for financial decision making. The hybrid agent was trained in a high-fidelity simulation environment that includes realistic market frictions and a risk-adjusted reward function. Backtesting results on unseen data indicate that the hybrid agent consistently performs better than its traditional counterpart. It achieves a total return of $21.2 \%$, which is higher than the $\mathbf{1 8 . 5 \%}$ return from the classical model. Additionally, risk-adjusted performance has clearly improved. The hybrid agent’s Sortino Ratio is $32.6 \%$ higher and its Sharpe Ratio is $26.4 \%$ higher. Its maximum drawdown is also lower. These findings demonstrate that quantum models are able to detect minute market relationships that conventional approaches might miss. As a result, trading tactics become more reliable and successful. This research marks a substantial breakthrough in the application of quantum technologies to challenging computational finance problems.

IEEE International Students' Conference on Electrical, Electronics and Computer Science (SCEECS)•Jan 31, 2026•0 citations

Variational Quantum Circuit-Based Reinforcement Learning for Dynamic Portfolio Optimization

Vincent Gurgul, Ying Chen, Stefan Lessmann

This paper presents a Quantum Reinforcement Learning (QRL) solution to the dynamic portfolio optimization problem based on Variational Quantum Circuits. The implemented QRL approaches are quantum analogues of the classical neural-network-based Deep Deterministic Policy Gradient and Deep Q-Network algorithms. Through an empirical evaluation on real-world financial data, we show that our quantum agents achieve risk-adjusted performance comparable to, and in some cases exceeding, that of classical Deep RL models with several orders of magnitude more parameters. However, while quantum circuit execution is inherently fast at the hardware level, practical deployment on cloud-based quantum systems introduces substantial latency, making end-to-end runtime currently dominated by infrastructural overhead and limiting practical applicability. Taken together, our results suggest that QRL is theoretically competitive with state-of-the-art classical reinforcement learning and may become practically advantageous as deployment overheads diminish. This positions QRL as a promising paradigm for dynamic decision-making in complex, high-dimensional, and non-stationary environments such as financial markets. The complete codebase is released as open source at: https://github.com/VincentGurgul/qrl-dpo-public

cs.LGCross-listedarXiv:2601.18811•Jan 21, 2026•0 citations

Deep Learning and Optimization Approaches in An Optimized Equivariant Split Attention Quantum Neural Network Based Recommendation System for Stock Market Prediction: A Review

Chatmanee Mardaniyan

Financial markets are complex, nonlinear, and highly dynamic systems, making accurate stock market prediction a challenging task. Traditional statistical and machine learning models often fail to capture the intricate temporal dependencies and high-dimensional interactions present in financial data. This review explores advanced approaches integrating deep learning, quantum computing, equivariant neural networks, and split attention mechanisms for stock market prediction and recommendation systems. Quantum neural networks leverage principles such as superposition and entanglement to enhance feature representation and computational efficiency, while equivariant architectures improve generalization by preserving structural relationships in data. Split attention mechanisms further enhance model performance by capturing both local and global temporal dependencies. The study also examines optimization strategies, including gradient-based methods and evolutionary algorithms, for efficient training of hybrid quantum-classical models. Additionally, the integration of recommendation systems enables personalized investment decision-making by combining market data with user preferences. Evaluations on benchmark financial datasets demonstrate improved prediction accuracy, scalability, and robustness compared to conventional models. Overall, the proposed framework offers a promising direction for developing intelligent, efficient, and next-generation financial forecasting systems.

International Journal of Electrical Electronics and Computer Systems•May 10, 2025•0 citations

Quantum-Enhanced Reinforcement Learning with LSTM Forecasting Signals for Optimizing Fintech Trading Decisions

Yen-Ku Liu, Yi Pan, Pei-Fan Lu +2 more

Financial trading environments are characterized by high volatility, numerous macroeconomic signals, and dynamically shifting market regimes, where traditional reinforcement learning methods often fail to deliver breakthrough performance. In this study, we design a reinforcement learning framework tailored for financial systems by integrating quantum circuits. We compare (1) the performance of classical A3C versus quantum A3C algorithms, and (2) the impact of incorporating LSTM-based predictions of the following week's economic trends on learning outcomes. The experimental framework adopts a custom Gymnasium-compatible trading environment, simulating discrete trading actions and evaluating rewards based on portfolio feedback. Experimental results show that quantum models—especially when combined with predictive signals—demonstrate superior performance and stability under noisy financial conditions, even with shallow quantum circuit depth.

arXiv:2507.12835•IEEE International Conference on Quantum Computing and Engineering (QCE)•Aug 30, 2025•3 citations

Quantum-Enhanced Deep Learning for Financial Anomaly Detection

Rayane Aggoune, Abdelhak Merizig

Financial markets in the MENA region face critical challenges in detecting anomalies within high-frequency trading and cross-border payment systems, where traditional machine learning approaches struggle with extreme dimensionality, class imbalance, and real-time constraints.This paper presents a theoretical quantum-enhanced deep learning framework addressing these challenges through hybrid quantum-classical architectures.We propose a novel hybrid architecture integrating variational quantum circuits (VQC) for feature extraction with transformer-based temporal modeling, achieving a theoretical parameter reduction of 40-60% over equivalent classical architectures.The framework identifies conditions for quantum advantage: high-dimensional sparse features (d > 100), extreme class imbalance (< 0.5% anomaly rate), and distancebased detection.All performance figures are theoretical projections from the literature; empirical validation is designated as future work.Our comparative analysis reveals that quantum kernel methods show theoretical improvement potential over classical baselines under these conditions.

Advances in economics, business and management research/Advances in Economics, Business and Management Research•Jan 1, 2026•0 citations

A Cirq-Enhanced Quantum Reinforcement Learning Model for High-Frequency Trading Optimization

Santosh Kumar Yadav, Tavleen Kaur, Simer Khurmi

The main goal of the proposed Quantum Reinforcement Learning (QRL) model that operates through Cirq framework serves to deliver competitive results in highfrequency trading environments in dynamic financial markets. Quantum parallel computing techniques provide to classical reinforcement learning methods a solution for their computational complexity and adaptability problems. The designed quantum-classical trading algorithm shows better market decisions along with quicker market reactions especially during periods of market volatility. The study investigates quantum-enhanced trading implementation methods and establishes three major research goals that include quantum scalability approaches, protecting quantum performance and building hybrid systems integrated with quantum and classical components.

International Conference on Computing for Sustainable Global Development•Apr 2, 2025•0 citations
Financial market prediction and optimal trading strategy development remain challenging due to market complexity and volatility. Our research in quantum finance and reinforcement learning for decision-making demonstrates the approach of quantum-classical hybrid algorithms to tackling real-world finan-cial challenges. In this respect, we corroborate the concept with rigorous backtesting and validate the framework's performance under realistic market conditions, by including fixed transaction cost per trade. This paper introduces a Quantum Attention Deep Q-Network (QADQN) approach to address these challenges through quantum-enhanced reinforcement learning. Our QADQN architecture uses a variational quantum circuit inside a traditional deep Q-learning framework to take advantage of possible quantum advantages in decision-making. We gauge the QADQN agent's performance on historical data from major market indices, including the S&P 500. We evaluate the agent's learning process by examining its reward accumulation and the effectiveness of its experience replay mechanism. Our empirical results demonstrate the QADQN's superior performance, achieving better risk-adjusted returns with Sortino ratios of 1.28 and 1.19 for non-overlapping and overlapping test periods respectively, indicating effective downside risk management.
This Paper shows information about the High Speed Stock Trading, In todays era the normal computers are struggling to identify and find the complex market patterns and strategies. So in order to solve this issue we built a new system that is a combination of quantum computing and classical computing in which Reinforcement Learning (a way for computers to learn with trial and error) is used with Quantum Machine Learning to make smarter trading decisions and strategies. Specially, we have used a quantum model (called a Variational Quantum classifier) as a part of Deep Q Network agent to help the system learning better trading strategies. Our goal is to use the superior representational power of quantum feature spaces for financial decision making. The hybrid agent was trained in a high-fidelity simulation environment that includes realistic market frictions and a risk-adjusted reward function. Backtesting results on unseen data indicate that the hybrid agent consistently performs better than its traditional counterpart. It achieves a total return of 21.2%21.2 \%21.2%, which is higher than the 18.5%\mathbf{1 8 . 5 \%}18.5% return from the classical model. Additionally, risk-adjusted performance has clearly improved. The hybrid agent’s Sortino Ratio is 32.6%32.6 \%32.6% higher and its Sharpe Ratio is 26.4%26.4 \%26.4% higher. Its maximum drawdown is also lower. These findings demonstrate that quantum models are able to detect minute market relationships that conventional approaches might miss. As a result, trading tactics become more reliable and successful. This research marks a substantial breakthrough in the application of quantum technologies to challenging computational finance problems.
This paper presents a Quantum Reinforcement Learning (QRL) solution to the dynamic portfolio optimization problem based on Variational Quantum Circuits. The implemented QRL approaches are quantum analogues of the classical neural-network-based Deep Deterministic Policy Gradient and Deep Q-Network algorithms. Through an empirical evaluation on real-world financial data, we show that our quantum agents achieve risk-adjusted performance comparable to, and in some cases exceeding, that of classical Deep RL models with several orders of magnitude more parameters. However, while quantum circuit execution is inherently fast at the hardware level, practical deployment on cloud-based quantum systems introduces substantial latency, making end-to-end runtime currently dominated by infrastructural overhead and limiting practical applicability. Taken together, our results suggest that QRL is theoretically competitive with state-of-the-art classical reinforcement learning and may become practically advantageous as deployment overheads diminish. This positions QRL as a promising paradigm for dynamic decision-making in complex, high-dimensional, and non-stationary environments such as financial markets. The complete codebase is released as open source at: https://github.com/VincentGurgul/qrl-dpo-public
Financial markets are complex, nonlinear, and highly dynamic systems, making accurate stock market prediction a challenging task. Traditional statistical and machine learning models often fail to capture the intricate temporal dependencies and high-dimensional interactions present in financial data. This review explores advanced approaches integrating deep learning, quantum computing, equivariant neural networks, and split attention mechanisms for stock market prediction and recommendation systems. Quantum neural networks leverage principles such as superposition and entanglement to enhance feature representation and computational efficiency, while equivariant architectures improve generalization by preserving structural relationships in data. Split attention mechanisms further enhance model performance by capturing both local and global temporal dependencies. The study also examines optimization strategies, including gradient-based methods and evolutionary algorithms, for efficient training of hybrid quantum-classical models. Additionally, the integration of recommendation systems enables personalized investment decision-making by combining market data with user preferences. Evaluations on benchmark financial datasets demonstrate improved prediction accuracy, scalability, and robustness compared to conventional models. Overall, the proposed framework offers a promising direction for developing intelligent, efficient, and next-generation financial forecasting systems.
Financial trading environments are characterized by high volatility, numerous macroeconomic signals, and dynamically shifting market regimes, where traditional reinforcement learning methods often fail to deliver breakthrough performance. In this study, we design a reinforcement learning framework tailored for financial systems by integrating quantum circuits. We compare (1) the performance of classical A3C versus quantum A3C algorithms, and (2) the impact of incorporating LSTM-based predictions of the following week's economic trends on learning outcomes. The experimental framework adopts a custom Gymnasium-compatible trading environment, simulating discrete trading actions and evaluating rewards based on portfolio feedback. Experimental results show that quantum models—especially when combined with predictive signals—demonstrate superior performance and stability under noisy financial conditions, even with shallow quantum circuit depth.
Financial markets in the MENA region face critical challenges in detecting anomalies within high-frequency trading and cross-border payment systems, where traditional machine learning approaches struggle with extreme dimensionality, class imbalance, and real-time constraints.This paper presents a theoretical quantum-enhanced deep learning framework addressing these challenges through hybrid quantum-classical architectures.We propose a novel hybrid architecture integrating variational quantum circuits (VQC) for feature extraction with transformer-based temporal modeling, achieving a theoretical parameter reduction of 40-60% over equivalent classical architectures.The framework identifies conditions for quantum advantage: high-dimensional sparse features (d > 100), extreme class imbalance (< 0.5% anomaly rate), and distancebased detection.All performance figures are theoretical projections from the literature; empirical validation is designated as future work.Our comparative analysis reveals that quantum kernel methods show theoretical improvement potential over classical baselines under these conditions.
The main goal of the proposed Quantum Reinforcement Learning (QRL) model that operates through Cirq framework serves to deliver competitive results in highfrequency trading environments in dynamic financial markets. Quantum parallel computing techniques provide to classical reinforcement learning methods a solution for their computational complexity and adaptability problems. The designed quantum-classical trading algorithm shows better market decisions along with quicker market reactions especially during periods of market volatility. The study investigates quantum-enhanced trading implementation methods and establishes three major research goals that include quantum scalability approaches, protecting quantum performance and building hybrid systems integrated with quantum and classical components.