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:2507.12835 · IEEE International Conference on Quantum Computing and Engineering (QCE)

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

Yen-Ku Liu, Yi Pan, Pei-Fan Lu, Yun‐Cheng Tsai, Samuel Yen-Chi Chen

Published Aug 30, 2025• 10 citations
arXivHTMLPDF

Abstract

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.

DOI
10.1109/qce65121.2025.10325

Related papers

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

Quantum Reinforcement Learning Trading Agent for Sector Rotation in the Taiwan Stock Market

Chi-Sheng Chen, Xinyu Zhang, Yuxi Chen

We propose a hybrid quantum-classical reinforcement learning framework for sector rotation in the Taiwan stock market. Our system employs Proximal Policy Optimization (PPO) as the backbone algorithm and integrates both classical architectures (LSTM, Transformer) and quantum-enhanced models (QNN, QRWKV, QASA) as policy and value networks. An automated feature engineering pipeline extracts financial indicators from capital share data to ensure consistent model input across all configurations. Empirical backtesting reveals a key finding: although quantum-enhanced models consistently achieve higher training rewards, they underperform classical models in real-world investment metrics such as cumulative return and Sharpe ratio. This discrepancy highlights a core challenge in applying reinforcement learning to financial domains-namely, the mismatch between proxy reward signals and true investment objectives. Our analysis suggests that current reward designs may incentivize overfitting to short-term volatility rather than optimizing risk-adjusted returns. This issue is compounded by the inherent expressiveness and optimization instability of quantum circuits under Noisy Intermediate-Scale Quantum (NISQ) constraints. We discuss the implications of this reward-performance gap and propose directions for future improvement, including reward shaping, model regularization, and validation-based early stopping. Our work offers a reproducible benchmark and critical insights into the practical challenges of deploying quantum reinforcement learning in real-world finance.

arXiv:2506.20930•IEEE International Conference on Quantum Computing and Engineering (QCE)•Aug 30, 2025•8 citations

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

Siddhant Dutta, Nouhaila Innan, Alberto Marchisio +2 more

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.

arXiv:2408.03088•IEEE International Conference on Quantum Computing and Engineering (QCE)•Sep 15, 2024•40 citations

Quantum-Enhanced Forecasting for Deep Reinforcement Learning in Algorithmic Trading

Junhao Chen, Yu-Chien Huang, Yun‐Cheng Tsai +1 more

The convergence of quantum-inspired neural networks and deep reinforcement learning offers a promising avenue for financial trading. We implemented a trading agent for USD/TWD by integrating Quantum Long Short-Term Memory (QLSTM) for short-term trend prediction with Quantum Asynchronous Advantage Actor-Critic (QA3C), a quantum-enhanced variant of the classical A3C. Trained on data from 2000-01-01 to 2025-04-30 (80\% training, 20\% testing), the long-only agent achieves 11.87\% return over around 5 years with 0.92\% max drawdown, outperforming several currency ETFs. We detail state design (QLSTM features and indicators), reward function for trend-following/risk control, and multi-core training. Results show hybrid models yield competitive FX trading performance. Implications include QLSTM's effectiveness for small-profit trades with tight risk and future enhancements. Key hyperparameters: QLSTM sequence length$=$4, QA3C workers$=$8. Limitations: classical quantum simulation and simplified strategy. \footnote{The views expressed in this article are those of the authors and do not represent the views of Wells Fargo. This article is for informational purposes only. Nothing contained in this article should be construed as investment advice. Wells Fargo makes no express or implied warranties and expressly disclaims all legal, tax, and accounting implications related to this article.

arXiv:2509.09176•IEEE Globecom Workshops (GC Wkshps)•Dec 8, 2025•5 citations

Quantum-AI Financial Forecasting for Portfolio Optimization and Intelligent Investment Decision-Making

R. Deepa, Arasuraja Ganesan, Umidbek M. Abdalov +3 more

The interplay between Quantum computing and Artificial Intelligence is transforming the financial analytics industry through the ability to process complex and high-dimensional financial data faster to make investment decisions. The classical franchise forecasting and risk control system is not effective in areas of non-linearity, market turbulence, and realtime flexibility, which tend to result in suboptimal asset allocation and slow reaction to unforeseen market changes. Such constraints make it impossible to predict correctly and mitigate the risks in dynamic financial settings. The paper will present a new model, Q-DARWIN (Quantum-Driven Adaptive Risk and Weighted Intelligence Network). The model combines variational quantum circuits with adaptive deep reinforcement learning to optimize portfolio allocation. A quantum-classical pipeline uses the probability of a financial asset to encode financial data into quantum states, and a self-evolving risk module to dynamically optimize asset weights, based on probabilistic learning and correlation mapping inspired by entanglement. Experimental simulations demonstrate that Q-DARWIN offers superior forecasting capability, lower portfolio volatility, and faster convergence than classical AI and statistical models, especially in high-frequency trading. A scaled solution to real-time financial planning and risk management is proposed, offering a viable and efficient approach, and the role of quantum-enhanced intelligence in modern portfolio optimization is discussed as transformative.

International Conference on Next-Gen Intelligent Computing and Applications (ICONICA)•Aug 1, 2026•0 citations

A Hybrid Quantum Circuit Born Machine Framework for Financial Volatility Forecasting: Quantum-Assisted Training and Classical Inference

Yixiong Chen

Accurate financial volatility forecasting is crucial but challenged by the non-linear, highly correlated nature of market data. Recently, quantum computing has emerged as a promising paradigm for solving complex high-dimensional sampling problems. To harness this, we propose a novel hybrid framework combining the temporal representation power of classical neural networks with the distribution-learning capabilities of quantum models. Specifically, we integrate a Long Short-Term Memory (LSTM) network with a Quantum Circuit Born Machine (QCBM). The LSTM extracts dynamic features, while the QCBM acts as a learnable generative prior modeling complex market distributions to guide forecasting. Evaluated on 5-minute high-frequency data from the SSE Composite and CSI 300 indices, our model significantly outperforms a classical LSTM baseline across MSE, RMSE, and QLIKE metrics. Furthermore, by introducing a stochastic ``Drop-Prior" mechanism during training, the LSTM implicitly distills structured information from the quantum prior. This establishes a pragmatic paradigm of ``quantum-assisted training with classical-efficient inference", whereby the model retains its quantum-enhanced accuracy even when the quantum module is entirely disabled during deployment. This demonstrates a practical pathway for leveraging quantum computing to enhance classical models without real-time quantum inference latency.

cs.LGCross-listedarXiv:2603.09789•Mar 11, 2026•0 citations
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.
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.
We propose a hybrid quantum-classical reinforcement learning framework for sector rotation in the Taiwan stock market. Our system employs Proximal Policy Optimization (PPO) as the backbone algorithm and integrates both classical architectures (LSTM, Transformer) and quantum-enhanced models (QNN, QRWKV, QASA) as policy and value networks. An automated feature engineering pipeline extracts financial indicators from capital share data to ensure consistent model input across all configurations. Empirical backtesting reveals a key finding: although quantum-enhanced models consistently achieve higher training rewards, they underperform classical models in real-world investment metrics such as cumulative return and Sharpe ratio. This discrepancy highlights a core challenge in applying reinforcement learning to financial domains-namely, the mismatch between proxy reward signals and true investment objectives. Our analysis suggests that current reward designs may incentivize overfitting to short-term volatility rather than optimizing risk-adjusted returns. This issue is compounded by the inherent expressiveness and optimization instability of quantum circuits under Noisy Intermediate-Scale Quantum (NISQ) constraints. We discuss the implications of this reward-performance gap and propose directions for future improvement, including reward shaping, model regularization, and validation-based early stopping. Our work offers a reproducible benchmark and critical insights into the practical challenges of deploying quantum reinforcement learning in real-world finance.
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.
The convergence of quantum-inspired neural networks and deep reinforcement learning offers a promising avenue for financial trading. We implemented a trading agent for USD/TWD by integrating Quantum Long Short-Term Memory (QLSTM) for short-term trend prediction with Quantum Asynchronous Advantage Actor-Critic (QA3C), a quantum-enhanced variant of the classical A3C. Trained on data from 2000-01-01 to 2025-04-30 (80\% training, 20\% testing), the long-only agent achieves 11.87\% return over around 5 years with 0.92\% max drawdown, outperforming several currency ETFs. We detail state design (QLSTM features and indicators), reward function for trend-following/risk control, and multi-core training. Results show hybrid models yield competitive FX trading performance. Implications include QLSTM's effectiveness for small-profit trades with tight risk and future enhancements. Key hyperparameters: QLSTM sequence length$=4,QA3Cworkers4, QA3C workers4,QA3Cworkers=$8. Limitations: classical quantum simulation and simplified strategy. \footnote{The views expressed in this article are those of the authors and do not represent the views of Wells Fargo. This article is for informational purposes only. Nothing contained in this article should be construed as investment advice. Wells Fargo makes no express or implied warranties and expressly disclaims all legal, tax, and accounting implications related to this article.
The interplay between Quantum computing and Artificial Intelligence is transforming the financial analytics industry through the ability to process complex and high-dimensional financial data faster to make investment decisions. The classical franchise forecasting and risk control system is not effective in areas of non-linearity, market turbulence, and realtime flexibility, which tend to result in suboptimal asset allocation and slow reaction to unforeseen market changes. Such constraints make it impossible to predict correctly and mitigate the risks in dynamic financial settings. The paper will present a new model, Q-DARWIN (Quantum-Driven Adaptive Risk and Weighted Intelligence Network). The model combines variational quantum circuits with adaptive deep reinforcement learning to optimize portfolio allocation. A quantum-classical pipeline uses the probability of a financial asset to encode financial data into quantum states, and a self-evolving risk module to dynamically optimize asset weights, based on probabilistic learning and correlation mapping inspired by entanglement. Experimental simulations demonstrate that Q-DARWIN offers superior forecasting capability, lower portfolio volatility, and faster convergence than classical AI and statistical models, especially in high-frequency trading. A scaled solution to real-time financial planning and risk management is proposed, offering a viable and efficient approach, and the role of quantum-enhanced intelligence in modern portfolio optimization is discussed as transformative.
Accurate financial volatility forecasting is crucial but challenged by the non-linear, highly correlated nature of market data. Recently, quantum computing has emerged as a promising paradigm for solving complex high-dimensional sampling problems. To harness this, we propose a novel hybrid framework combining the temporal representation power of classical neural networks with the distribution-learning capabilities of quantum models. Specifically, we integrate a Long Short-Term Memory (LSTM) network with a Quantum Circuit Born Machine (QCBM). The LSTM extracts dynamic features, while the QCBM acts as a learnable generative prior modeling complex market distributions to guide forecasting. Evaluated on 5-minute high-frequency data from the SSE Composite and CSI 300 indices, our model significantly outperforms a classical LSTM baseline across MSE, RMSE, and QLIKE metrics. Furthermore, by introducing a stochastic ``Drop-Prior" mechanism during training, the LSTM implicitly distills structured information from the quantum prior. This establishes a pragmatic paradigm of ``quantum-assisted training with classical-efficient inference", whereby the model retains its quantum-enhanced accuracy even when the quantum module is entirely disabled during deployment. This demonstrates a practical pathway for leveraging quantum computing to enhance classical models without real-time quantum inference latency.