This study investigates uncertainty quantification (UQ) using quantum-classical hybrid machine learning (ML) models for applications in complex and dynamic fields, such as attaining resiliency in supply chain digital twins and financial risk assessment. Although quantum feature transformations have been integrated into ML models for complex data tasks, a gap exists in determining their impact on UQ within their hybrid architectures (quantum-classical approach). This work applies existing UQ techniques for different models within a hybrid framework, examining how quantum feature transformation affects uncertainty propagation. Increasing qubits from 4 to 16 shows varied model responsiveness to outlier detection (OD) samples, which is a critical factor for resilient decision-making in dynamic environments. This work shows how quantum computing techniques can transform data features for UQ, particularly when combined with classical methods.
This study investigates uncertainty quantification (UQ) using quantum-classical hybrid machine learning (ML) models for applications in complex and dynamic fields, such as attaining resiliency in supply chain digital twins and financial risk assessment. Although quantum feature transformations have been integrated into ML models for complex data tasks, a gap exists in determining their impact on UQ within their hybrid architectures (quantum-classical approach). This work applies existing UQ techniques for different models within a hybrid framework, examining how quantum feature transformation affects uncertainty propagation. Increasing qubits from 4 to 16 shows varied model responsiveness to outlier detection (OD) samples, which is a critical factor for resilient decision-making in dynamic environments. This work shows how quantum computing techniques can transform data features for UQ, particularly when combined with classical methods.
Sustainable supply chains are becoming increasingly important as businesses strive to reduce environmental impact while maintaining efficiency and profitability. One emerging solution is Quantum Intelligence (Quantum AI)—a powerful combination of quantum computing and artificial intelligence that can handle highly complex and data-intensive supply chain problems. Quantum AI leverages unique quantum principles such as superposition and entanglement to explore a vast number of possible solutions simultaneously. This enables better decision-making in areas like production scheduling, inventory management, and emissions forecasting. As a result, organizations can optimize delivery routes, reduce operational costs, and significantly lower carbon emissions, contributing to more sustainable and environmentally responsible supply chains. A key approach in this field is the hybrid quantum-classical model, which combines the data-processing strengths of classical computing with the advanced computational capabilities of quantum systems. This hybrid approach helps overcome current limitations in quantum hardware, such as noise, limited qubits, and high error rates, making Quantum AI more practical for real-world applications. In addition, integrating technologies like the Internet of Things (IoT), blockchain, and digital twins further enhances supply chain performance. IoT devices provide real-time data from sensors, blockchain ensures transparency and traceability, and digital twins allow simulation of supply chain operations to predict environmental impacts and test different scenarios. Overall, Quantum AI represents a promising step toward building smarter, more efficient, and sustainable supply chains that can adapt to modern challenges while supporting global environmental goals.
This investigation gives introduction of 'PRABAX' Quantum Supply Chain Optimization Model, using quantum optimization techniques in decision making processes of supply chains. By using the combination of the latest developments of quantum computing with operational practices for routing, scheduling, inventory, demand forecasting, the model covers the prevalent challenges relating to scalability, uncertainty and resilience. A systematic literature review based on PRISMA guidelines for synthesising both classical and quantum optimisation strategies. The study introduces Quantum Annealing (QA), Quantum Approximate Optimization Algorithm (QAOA), Quantum Machine Learning (QML), and Hybrid Quantum - Classical Methodology into a coherent concept. To capture the dynamics of the context, such issues as mediating variables such as the choice of algorithm and refining a hybrid model and of moderating factors such as the maturity of hardware and data integrity, and the integration constancy are investigated. The implementation of QE within the 'PRABAX' framework ensures the improvement of the resilience of the supply chains, improve forecasting accuracy, and reduce the computational efficiency. Empirical demos suggest that hybrid workflows that incorporate quantum capabilities with the practical constraints of current available hardware provide the most feasible short term trajectory. The proposed framework helps managers and policy makers to understand the effective adoption pathways. It advises a phased implementation approach with initial short routinely hybrid pilot initiatives, followed by the medium-term system integration, and long run transition to full quantum native functioning. The 'PRABAX' model is both an extension to the theory of optimisation and a combination of quantum concepts, which places the idea of hybrid frameworks as an emerging paradigm in the field of supply chain literature. It bridges the gap between developments in computational science to established theories and models about resilience, dynamic capabilities and resource-based views, and represents quantum optimisation as an important strategic asset. This study represents the first fully established framework for the optimisation of quantum enabled supply chains that clearly outlines the hypotheses that can be tested as well as clear strategies for their adoption, helping to guide future academic research and practices.
This work investigates a hybrid quantum-classical machine learning methodology that combines deep learning with quantum computing to improve predictive analytics. The method starts by changing basic input features into the best mixed forms using classical weight matrices and quantum state encoding. A unitary operator refines quantum states to enhance feature extraction and representation. Gradient-based alterations repeatedly modify feature weights during optimization to improve accuracy. Quantum circuits not only change data but also enhance system separability and resilience. Normalizing and enhancing extracted properties using quantum and classical transformations ensures stability and consistency. Performance trials demonstrate that the hybrid technique improves accuracy, precision, recall, computational complexity, execution time, and energy economy. The hybrid model always outperforms machine learning, deep learning, and quantum mechanics-based approaches. The technique is now more scalable, making enormous data sets easier to analyze. Faster convergence rates and noise tolerance improve model performance in real-world applications. The findings suggest that quantum advances and classical learning approaches improve model interpretability and decision-making reliability. The research found hybrid quantum-classical machine learning to be a powerful, scalable, and efficient predictive modeling solution. This method improves precision while conserving computing power. By using both paradigms, the technique provides deeper insights and better predictions. As a major facilitator for future AI-driven applications, the hybrid model provides a possible solution for difficult machine learning challenges. These developments make hybrid models available.
As organizations navigate increasingly complex operational environments, conventional risk management models often fail to capture the nonlinear, high-dimensional interactions that drive modern crises. The convergence of artificial intelligence (AI) and quantum computing offers a transformative framework for predictive risk assessment and adaptive crisis response. This study explores the design and application of AI–quantum hybrid models that integrate quantum-enhanced computation with machine learning to improve the accuracy, speed, and scalability of organizational risk forecasting systems. The proposed framework employs quantum machine learning (QML) algorithms—such as the Quantum Support Vector Machine (QSVM) and Quantum Neural Networks (QNNs)—in conjunction with classical deep learning methods for multi-layered risk prediction and decision optimization. By leveraging quantum superposition and entanglement, the system enhances the exploration of correlated variables in financial, operational, and reputational risk domains. Empirical simulations demonstrate that hybrid AI–quantum approaches outperform purely classical models in identifying latent crisis patterns, managing uncertainty propagation, and optimizing mitigation strategies under dynamic constraints. The study underscores the strategic importance of quantum-ready organizational resilience frameworks, emphasizing interpretability, data security, and ethical governance in hybrid model deployment. By merging predictive analytics with quantum optimization, this research establishes a pathway toward proactive, intelligent, and resilient organizational crisis management in an era of exponential technological change.
The study presents the earliest effort to conceptualize SCM integration with quantum computing principles, providing dynamic capabilities for SCM. It proposes a unique interdisciplinary framework that demonstrates where hybrid quantum-classical approaches can realise value, and specifies the conditions that organizations must meet to adopt such methods. In this article, a conceptual framework has been proposed for HQCSCO. This framework facilitates key decision-making areas such as inventory optimisation, production scheduling, and logistics routing, where quantum-enhanced algorithms could supplement classical models to enhance performance. At the managerial level, the framework helps manufacturing leaders to determine viability, prioritize high-impact use cases, and develop future-ready digital capabilities that enhance cost efficiency, agility, and resilience. The research provides a conceptually-based baseline of quantum-facile supply chains and offers a research agenda to investigate the strategic, ethical, and operational implications thereof.
Software Requirement Risk Analysis is crucial for detecting potential failures early in the Software Development Life Cycle (SDLC). Existing machine learning (ML) and deep learning (DL) methods provide promising results, but they often struggle with capturing complex dependencies in requirement data. This paper introduces a novel hybrid Quantum-Classical Machine Learning (QML) framework to improve the accuracy and reliability of requirement risk classification. The dataset was preprocessed using label encoding, Synthetic Minority Oversampling Technique (SMOTE), ANOVA F-test (SelectKBest) for feature selection, and feature scaling to enable quantum circuit integration. Strongly entangling quantum circuits were implemented using the Qiskit framework to generate quantumenhanced features, which were fused with classical features. Four hybrid models-RF + QML, LGBM + QML, LR + QML, and Q-Kernel + MLP-were trained and evaluated. Experimental results show that the proposed Q-Kernel + MLP model achieved the best performance with 97.76% accuracy, 97.92% precision, 97.76% recall, and an F 1 -score of 97.77%, outperforming classical baselines by up to 4%. These findings highlight the potential of quantum-enhanced learning in software engineering, offering a scalable and robust solution for early risk detection and supporting more reliable project planning and software quality assurance.