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

Quantum Annealing for Customer Segmentation: A Proof-of-Concept QUBO Framework for Supply Chain Clustering

Raphaël Bouchet, Alena Puchkova

Published Nov 11, 2026• 0 citations
Publisher

Abstract

This article investigates the potential of quantum clustering, specifi cally through quantum annealing, to enhance supply chain segmentation compared with classical K-Means. Using a proof-of-concept framework, clustering is translated into a Quadratic Unconstrained Binary Optimisation formulation, tested on customer datasets via both classical Simulated Annealing and D-Wave’s Leap hybrid solver, with penalty parameter optimisation introduced to address solver sensitivity. Performance is benchmarked against K-Means on runtime, accuracy metrics, and scalability, across dataset sizes from 200 to 5,000 points. Results show that while K-Means maintains superior inertia and stability, the hybrid quantum approach achieves faster solver-reported runtimes and, on a simplifi ed 200-point, two-feature benchmark, delivers improved silhouette, Davies-Bouldin, Calinski-Harabasz, and Dunn scores once penalties are optimised — metrics which, it is noted, reward the balanced partitions structurally favoured by the pairwise QUBO objective. However, scalability remains constrained by current qubit capacity and solver access, limiting practical deployment beyond mid-sized datasets. The study concludes that classical methods remain dominant for industrial-scale segmentation; the demonstrated framework, penalty-optimisation pipeline, and objective-level analysis nonetheless provide a documented foundation, grounded in a customer segmentation case study, upon which future quantum-assisted supply chain clustering can build as hardware matures.

DOI
10.17863/cam.136908

Related papers

Quantum Annealing for Machine Learning: Applications in Feature Selection, Instance Selection, and Clustering

Pomeroy, Chloe, Aleksandar Pramov, Karishma Thakrar +1 more

This paper explores the applications of quantum annealing (QA) and classical simulated annealing (SA) to a suite of combinatorial optimization problems in machine learning, namely feature selection, instance selection, and clustering. We formulate each task as a Quadratic Unconstrained Binary Optimization (QUBO) problem and implement both quantum and classical solvers to compare their effectiveness. For feature selection, we propose several QUBO configurations that balance feature importance and redundancy, showing that quantum annealing (QA) produces solutions that are computationally more efficient. In instance selection, we propose a few novel heuristics for instance-level importance measures that extend existing methods. For clustering, we embed a classical-to-quantum pipeline, using classical clustering followed by QUBO-based medoid refinement, and demonstrate consistent improvements in cluster compactness and retrieval metrics. Our results suggest that QA can be a competitive and efficient tool for discrete machine learning optimization, even within the constraints of current quantum hardware.

arXiv:2507.15063•Jul 20, 2025•3 citations

Lookalike Clustering for Customer Segmentation: a Comparative Study of Quantum Annealing and Classical Algorithms

Benedetta Ferrari, Giuseppe Gnocchi, Manuel Iori +6 more

Customer segmentation is strategic for increasing business revenues, as it allows a company to offer tailored products and services. Companies have access to vast amounts of information to generate customer clusters. In the banking sector, for instance, transactional data may reveal several hidden customer characteristics. The lookalike clustering problem aims to expand an initial cluster by detecting similar customers from a larger set. In this work, we model the lookalike clustering problem as a Quadratic Unconstrained Binary Optimization problem and solve it by means of a Quantum Annealer (QA). We tune the penalization parameters of the QA through an adaptive subgradient-inspired algorithm. We then compare QA performance against those obtained by a Simulated Annealing and the classical integer programming solver Gurobi. The results show that QA, when properly tuned, is able to find the optimal solution for small instances of the problem, even when the number of variables exceeds the number of couplers of QA. It fails, instead, for larger ones, due to the high level of noise. The results also show that QA requires a very short time to generate feasible and optimal solutions compared to classical algorithms, thus proving its potential for the solution of fully connected graphs.

Genetic and Evolutionary Computation Conference Companion (GECCO Companion)•Jul 14, 2025•0 citations

Towards scalable quantum annealing for pooling and blending problems: A methodological proof-of-concept

Vasileios K. Mappas, Bogdan Dorneanu, Eduardo Nolasco +2 more

Industrial optimization challenges, such as the pooling and blending problem (PBP), require advanced computational methods to address non-convexity and scalability limitations in classical solvers. This work introduces a novel methodological framework for solving PBPs using quantum annealing (QA) that transforms the PBP into quadratic unconstrained binary optimization (QUBO) formulations at two resolution levels, enabling direct deployment on quantum annealers. Key innovations include a discretization technique tailored for PBP’s bilinear constraints and an embedding method optimized for current quantum hardware. Benchmarking against classical solvers focuses on Haverly’s classical three-stream PBP, enabling transparent comparison and development of quantum embedding and solution techniques. The proposed framework offers a scalable template for adapting similar engineering systems to quantum annealing architectures. Addressing genuine industrial-scale instances will require future advances in quantum hardware and embedding algorithms. The results demonstrate that QA exhibits the best performance among the examined alternatives, provide foundational insights towards leveraging QA in Process Systems Engineering.

Process Safety and Environmental Protection•Aug 24, 2025•2 citations

Quantum Computing for Logistics Optimization: Annealing in ULD Configuration and Disruption

Dr. V. A. Sharma

Quantum computing offers transformative potential for addressing complex combinatorial optimization challenges in logistics and supply chain management. This paper presents a comprehensive investigation of quantum annealing and hybrid quantum-classical algorithms applied to unit load device (ULD) configuration and disruption management in air cargo and multimodal logistics networks. We formulate the ULD loading and placement problem as a Quadratic Unconstrained Binary Optimization (QUBO) model that incorporates weight, volume, center-of-gravity, structural stress, and compatibility constraints. A stratified hybrid architecture spanning physical quantum hardware, algorithmic middleware, and decision-support layers is proposed. Through extensive numerical experiments and comparison with classical solvers, we demonstrate superior payload utilization (up to 96.5%), favorable computational scaling, and rapid disruption recovery. Real-world industry pilots, including quantum-assisted route optimization achieving substantial carbon emission reductions and hybrid solutions at major ports, are analyzed. Results indicate that while noisy intermediate-scale quantum (NISQ) hardware limitations persist, hybrid approaches already deliver measurable gains in operational efficiency, cost reduction, and supply-chain resilience. The work provides a practical roadmap for near-term adoption of quantum technologies in high-stakes logistics environments. Keywords— Quantum annealing, Unit load device (ULD), QUBO, Logistics optimization, Disruption management, Hybrid quantum-classical algorithms, Air cargo, Supply chain resilience

International Journal of Creative and Open Research in Engineering and Management•Aug 24, 2026•0 citations

Quantum Annealing Drives Real Enterprise Value

Akey Sungheetha, Rajesh Sharma R

Quantum computing is now evolving in different directions, with quantum annealing and gate-model approaches tackling different types of problems. This paper looks at how the shift from D-Wave’s annealing systems to hybrid quantum-classical models changes how companies adopt these technologies. The main issue is the gap between what quantum hardware can do and what businesses need, especially for combinatorial optimization, machine learning, and cryptography.The focus includes D-Wave’s Pegasus topology processors, the 5,000-plus qubit Advantage system, and the new gate-model Gate Model 1 (Leap) integration layer. The goal is to gather real-world benchmarking data and design principles to find out which quantum method provides clear business benefits now and which challenges are still out of reach. The proposed framework connects problem structure, shown through Quadratic Unconstrained Binary Optimisation (QUBO) density, variable count, and constraint tightness, to processor suitability scores. This gives practical advice for deployment. This work is unique because it systematically compares the performance of annealing and gate models on typical industry cases. It includes methods for penalty-weight calibration, chain-break reduction through post-processing, and measuring hybrid solver delays. Simulation results show that annealing can provide time-to-solution improvements of up to 87% compared to classical branch-and-bound on dense graph problems with 512 logical variables. In contrast, gate-model circuits tackling the same problems face 3.4 times the delay due to current decoherence issues.

International Conference on Intelligent and Sustainable AI Systems (ICOSAAS)•Jul 1, 2026•0 citations

A Hybrid Quantum-Classical Approach for Solving QUBO Models in Blockchain-Enabled Supply Chain Inventory Management

L. Sherin Beevi, Ponsy R. K. Sathia Bhama, P. M. Joe Prathap +2 more

Managing inventory in large-scale supply chains necessitates quick, cost-effective decisions that adhere to constraints such as storage limits and variable demand. This paper describes a novel hybrid approach that uses both quantum and classical computers to tackle inventory problems structured as Quadratic Unconstrained Binary Optimization (QUBO). Each choice variable, such as restocking a product, is represented in binary form, with related costs and penalties built into the objective function. Business constraints are communicated indirectly using adjustable weights, allowing the model to remain unconstrained while discouraging unrealistic conclusions. Optimization is carried out using both classical methods like simulated annealing and quantum solvers such as D-Wave and QAOA, where a hybrid strategy selects the most viable solution. The results indicate that the hybrid system consistently produces lower total costs and better constraint compliance compared to individual solvers, especially for complex, high-dimensional datasets. To ensure secure, automated execution of these optimized decisions, a blockchain layer is introduced. Inventory actions—such as placing orders or updating stock—are carried out through smart contracts that provide tamper-proof, verifiable enforcement. By employing a lightweight Proof of Authority (PoA) mechanism, transaction validation remains fast while maintaining transparency across all nodes in the network. This integration of quantum optimization with blockchain automation enables a responsive and trustworthy framework for modern inventory management.

International Conference on Computing and Communications (COMPUTINGCON)•Sep 1, 2025•1 citation
This article investigates the potential of quantum clustering, specifi cally through quantum annealing, to enhance supply chain segmentation compared with classical K-Means. Using a proof-of-concept framework, clustering is translated into a Quadratic Unconstrained Binary Optimisation formulation, tested on customer datasets via both classical Simulated Annealing and D-Wave’s Leap hybrid solver, with penalty parameter optimisation introduced to address solver sensitivity. Performance is benchmarked against K-Means on runtime, accuracy metrics, and scalability, across dataset sizes from 200 to 5,000 points. Results show that while K-Means maintains superior inertia and stability, the hybrid quantum approach achieves faster solver-reported runtimes and, on a simplifi ed 200-point, two-feature benchmark, delivers improved silhouette, Davies-Bouldin, Calinski-Harabasz, and Dunn scores once penalties are optimised — metrics which, it is noted, reward the balanced partitions structurally favoured by the pairwise QUBO objective. However, scalability remains constrained by current qubit capacity and solver access, limiting practical deployment beyond mid-sized datasets. The study concludes that classical methods remain dominant for industrial-scale segmentation; the demonstrated framework, penalty-optimisation pipeline, and objective-level analysis nonetheless provide a documented foundation, grounded in a customer segmentation case study, upon which future quantum-assisted supply chain clustering can build as hardware matures.
This paper explores the applications of quantum annealing (QA) and classical simulated annealing (SA) to a suite of combinatorial optimization problems in machine learning, namely feature selection, instance selection, and clustering. We formulate each task as a Quadratic Unconstrained Binary Optimization (QUBO) problem and implement both quantum and classical solvers to compare their effectiveness. For feature selection, we propose several QUBO configurations that balance feature importance and redundancy, showing that quantum annealing (QA) produces solutions that are computationally more efficient. In instance selection, we propose a few novel heuristics for instance-level importance measures that extend existing methods. For clustering, we embed a classical-to-quantum pipeline, using classical clustering followed by QUBO-based medoid refinement, and demonstrate consistent improvements in cluster compactness and retrieval metrics. Our results suggest that QA can be a competitive and efficient tool for discrete machine learning optimization, even within the constraints of current quantum hardware.
Customer segmentation is strategic for increasing business revenues, as it allows a company to offer tailored products and services. Companies have access to vast amounts of information to generate customer clusters. In the banking sector, for instance, transactional data may reveal several hidden customer characteristics. The lookalike clustering problem aims to expand an initial cluster by detecting similar customers from a larger set. In this work, we model the lookalike clustering problem as a Quadratic Unconstrained Binary Optimization problem and solve it by means of a Quantum Annealer (QA). We tune the penalization parameters of the QA through an adaptive subgradient-inspired algorithm. We then compare QA performance against those obtained by a Simulated Annealing and the classical integer programming solver Gurobi. The results show that QA, when properly tuned, is able to find the optimal solution for small instances of the problem, even when the number of variables exceeds the number of couplers of QA. It fails, instead, for larger ones, due to the high level of noise. The results also show that QA requires a very short time to generate feasible and optimal solutions compared to classical algorithms, thus proving its potential for the solution of fully connected graphs.
Industrial optimization challenges, such as the pooling and blending problem (PBP), require advanced computational methods to address non-convexity and scalability limitations in classical solvers. This work introduces a novel methodological framework for solving PBPs using quantum annealing (QA) that transforms the PBP into quadratic unconstrained binary optimization (QUBO) formulations at two resolution levels, enabling direct deployment on quantum annealers. Key innovations include a discretization technique tailored for PBP’s bilinear constraints and an embedding method optimized for current quantum hardware. Benchmarking against classical solvers focuses on Haverly’s classical three-stream PBP, enabling transparent comparison and development of quantum embedding and solution techniques. The proposed framework offers a scalable template for adapting similar engineering systems to quantum annealing architectures. Addressing genuine industrial-scale instances will require future advances in quantum hardware and embedding algorithms. The results demonstrate that QA exhibits the best performance among the examined alternatives, provide foundational insights towards leveraging QA in Process Systems Engineering.
Quantum computing offers transformative potential for addressing complex combinatorial optimization challenges in logistics and supply chain management. This paper presents a comprehensive investigation of quantum annealing and hybrid quantum-classical algorithms applied to unit load device (ULD) configuration and disruption management in air cargo and multimodal logistics networks. We formulate the ULD loading and placement problem as a Quadratic Unconstrained Binary Optimization (QUBO) model that incorporates weight, volume, center-of-gravity, structural stress, and compatibility constraints. A stratified hybrid architecture spanning physical quantum hardware, algorithmic middleware, and decision-support layers is proposed. Through extensive numerical experiments and comparison with classical solvers, we demonstrate superior payload utilization (up to 96.5%), favorable computational scaling, and rapid disruption recovery. Real-world industry pilots, including quantum-assisted route optimization achieving substantial carbon emission reductions and hybrid solutions at major ports, are analyzed. Results indicate that while noisy intermediate-scale quantum (NISQ) hardware limitations persist, hybrid approaches already deliver measurable gains in operational efficiency, cost reduction, and supply-chain resilience. The work provides a practical roadmap for near-term adoption of quantum technologies in high-stakes logistics environments. Keywords— Quantum annealing, Unit load device (ULD), QUBO, Logistics optimization, Disruption management, Hybrid quantum-classical algorithms, Air cargo, Supply chain resilience
Quantum computing is now evolving in different directions, with quantum annealing and gate-model approaches tackling different types of problems. This paper looks at how the shift from D-Wave’s annealing systems to hybrid quantum-classical models changes how companies adopt these technologies. The main issue is the gap between what quantum hardware can do and what businesses need, especially for combinatorial optimization, machine learning, and cryptography.The focus includes D-Wave’s Pegasus topology processors, the 5,000-plus qubit Advantage system, and the new gate-model Gate Model 1 (Leap) integration layer. The goal is to gather real-world benchmarking data and design principles to find out which quantum method provides clear business benefits now and which challenges are still out of reach. The proposed framework connects problem structure, shown through Quadratic Unconstrained Binary Optimisation (QUBO) density, variable count, and constraint tightness, to processor suitability scores. This gives practical advice for deployment. This work is unique because it systematically compares the performance of annealing and gate models on typical industry cases. It includes methods for penalty-weight calibration, chain-break reduction through post-processing, and measuring hybrid solver delays. Simulation results show that annealing can provide time-to-solution improvements of up to 87% compared to classical branch-and-bound on dense graph problems with 512 logical variables. In contrast, gate-model circuits tackling the same problems face 3.4 times the delay due to current decoherence issues.
Managing inventory in large-scale supply chains necessitates quick, cost-effective decisions that adhere to constraints such as storage limits and variable demand. This paper describes a novel hybrid approach that uses both quantum and classical computers to tackle inventory problems structured as Quadratic Unconstrained Binary Optimization (QUBO). Each choice variable, such as restocking a product, is represented in binary form, with related costs and penalties built into the objective function. Business constraints are communicated indirectly using adjustable weights, allowing the model to remain unconstrained while discouraging unrealistic conclusions. Optimization is carried out using both classical methods like simulated annealing and quantum solvers such as D-Wave and QAOA, where a hybrid strategy selects the most viable solution. The results indicate that the hybrid system consistently produces lower total costs and better constraint compliance compared to individual solvers, especially for complex, high-dimensional datasets. To ensure secure, automated execution of these optimized decisions, a blockchain layer is introduced. Inventory actions—such as placing orders or updating stock—are carried out through smart contracts that provide tamper-proof, verifiable enforcement. By employing a lightweight Proof of Authority (PoA) mechanism, transaction validation remains fast while maintaining transparency across all nodes in the network. This integration of quantum optimization with blockchain automation enables a responsive and trustworthy framework for modern inventory management.