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

International Conference on Machine Learning and Computer Application (ICMLCA)

Optimization of credit scoring models combination based on quantum annealing

Xinyu Zheng, Yonghong Ma, Zhigang Song

Published Oct 27, 2023• 0 citations
Publisher

Abstract

The development of credit scoring models holds significant importance in banking for crediting operations. Combining multiple credit scoring models using a stacking generalization approach often yields improved results. However, selecting the optimal combination of credit scoring models is NP-Hard. In recent years, emerging quantum annealing (QA) techniques have shown promise in the field of combinatorial optimization and are considered potential solutions for NP-Hard problems. Hence, we propose an approach that employs QA for solving the credit scoring model combination optimization problem using a stacking generalization approach. By employing both auxiliary variable substitution and polynomial reduction methods, two distinct Quadratic Unconstrained Binary Optimization (QUBO) models suitable for quantum annealing are formulated. Experimental results demonstrate that the hybrid quantum annealing solver outperforms simulated annealing and simulated quantum annealing in terms of optimization capability across various problem sizes. The polynomial reduction and auxiliary variable substitution methods each exhibit their own advantages in terms of solution quality and computational efficiency.

DOI
10.1145/3650215.3650227

Related papers

Model Analysis and Application of Quantum Computers in Credit Scoring Card Combination Optimization

Xiaohan Zhou, Ruikun Zhang

In the context of business such as bank credit cards or related loans, banks score customers through credit scoring cards. Loan interest income and bad debt losses determined by the combination of thresholds of different credit scoring cards are key factors that determine the bank's final income. This paper mainly studies the combination optimization of credit scoring cards by establishing an optimization model and transforming it into a Quadratic Unconstrained Binary Optimization (QUBO) problem. First, the optimization problem of a single credit scoring card is studied, the data is preprocessed and zero-one integer programming model is established, then convert the objective function into a Hamiltonian to obtain an optimization model in the form of QUBO, and obtain the maximum bank income and the threshold of a single credit scoring card through the Simulated Annealing. Then, the credit scoring card combination optimization problem is studied. On the basis of the above research, variable substitution is used to reduce function degree, and a penalty function is introduced to obtain an unconstrained QUBO model for the combination problem. The D-Wave quantum annealing algorithm is used to obtain the optimal combination solution.

IEEE Data Driven Control and Learning Systems Conference (DDCLS)•May 17, 2024•0 citations

Application of QUBO model in credit score card combination optimization

Fengyuan Ma, Yujie He, Juan Hu

Credit cards are a rule by which banks rate their customers. Different credit scoring cards have different thresholds, corresponding to different pass rates and bad debt rates, which have a crucial impact on the bank's revenue. To help banks choose the best combination of credit scoring cards, so as to maximize revenue. Based on the triple credit card combination strategy of the bank, this paper establishes a mathematical programming model for solving the optimal combination. Aiming at the particularity of the binary decision variables, a constraint method is proposed to transform the quartic and quartic terms in the model into quadratic terms. Then, in order to balance the relationship between the objective function and the constraint conditions, the weighted penalty coefficient is further introduced by combining the entropy weight method. The model is transformed into QUBO(quadratic unconstrained binary optimization) model, and then combined with the bank's credit score card data, the optimal combination is solved by quantum annealing algorithm and verified by experiment. The experimental results show that this method has high precision and strong applicability in solving combinatorial optimization problems.

Highlights in Science Engineering and Technology•Oct 9, 2023•0 citations

Optimization of credit scorecard combinations based on quantum annealing algorithm

Bingze He, Xingyi Ji, Jiaxin Lv

With the development of the times, the usage of loan-related business is increasing. However, most of the credit score card portfolio methods used nowadays are manually designed and supplemented with computer calculations, so the bank yields are low. Therefore, it is of great interest to study the application of quantum computers in credit score card portfolio optimization for better rating of customer credit ratings. Based on the given credit score card data, a linear programming model is developed. Firstly, the data is processed into two sets of one-dimensional data by Python and the working range of the two sets of data is found. Secondly, after deriving the objective function expressions according to the given conditions, the data were visualized by building a 3D grid matrix with the pass rate and bad debt rate as the XOY plane and the final benefit to the bank as the Z axis. Subsequently, the decision variables in the linear programming model are converted into binary variables, and the original model is transformed into a QUBO model by converting the constraints into binary variables. After analyzing the QUBO model, the quantum annealing method is chosen to solve the optimal solution of the objective function. And based on this, the case of three selected credit score card combinations and any three credit score cards are considered.

Highlights in Science Engineering and Technology•Jul 30, 2023•1 citation

New QUBO Transformations to Improve Quantum and Simulated Annealing Performance for Quadratic Knapsack

Nicolás Borrajo, Juan Marcos Ramírez, Farzam Nosrati +3 more

Recent advances in quantum computing have shown great potential for solving combinatorial optimization problems. A notable example is the quadratic knapsack problem, a constrained binary optimization problem. However, current quantum-inspired algorithms require Quadratic Unconstrained Binary Optimization (QUBO) formulations. Transforming constrained optimization into QUBO impacts the algorithms' speed and efficiency. In this study, we evaluate five existing transformation methods and propose four novel approaches. We assess them by using Simulated Annealing (SA), and find that three of our approaches outperform existing methods in terms of execution time as well as quality and quantity of feasible solutions found. Also, we tested these transformations on a quantum annealer, which was unable to solve even small instances, due to limitations in connectivity and error rates. In general, our results highlight the advantages of the new approaches, which reduce the number of variables in the QUBO representation.

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

Application of Quantum Annealing Algorithm in The Combined Optimization of Credit Score Cards

Yixuan Jin, Rui Ye, Leqi Zhu

The country's lending modality has long been credit lending. In reality, banks originate multiple portfolios. Therefore, it is necessary to build a model to select an appropriate portfolio to maximize the final return of the bank. Quantum annealing algorithm is an optimization algorithm based on quantum computing, which can be used to solve complex optimization problems, evaluate the risk of different portfolios, and help investors to identify the potential risks and take appropriate measures. In this paper, the threshold information of 100 credit cards is collected, and each credit card corresponds to 10 thresholds. This paper tries to find the maximum 3 credit card threshold portfolio of bank loan income, so it establishes an optimization model, introduces 0-1 variables, establishes an objective income function to the QUBO model, and runs 10 times the premise to get the final portfolio of the highest income credit card thresholds through the quantum annealing algorithm. Finally, combining the results of the operation of the simulated annealing model, the speed and accuracy of the operation of the quantum ventilation is found.

Asia Conference on Algorithms, Computing and Machine Learning (CACML)•Mar 22, 2024•0 citations

Quantum Annealing Combinatorial Optimization (QACO)

Jincheng Zhang

This paper explores the application of Quantum Annealing (QA) to the field of combinatorial optimization. The core idea is to leverage the principles of quantum mechanics, specifically quantum tunneling, to efficiently solve complex optimization problems. We present a framework for utilizing QA to tackle problems represented as quadratic unconstrained binary optimization (QUBO) models. The methodology focuses on mapping the problem's constraints and objective function into a form suitable for QA hardware. We discuss the challenges involved in this mapping process, including the limitations of current QA devices and the need for careful problem formulation. Furthermore, we analyze the potential advantages of QA over classical optimization techniques, particularly concerning the exploration of a wider solution space. The research highlights the promise of QACO as a viable approach for tackling computationally demanding combinatorial optimization tasks, offering a novel method to enhance optimization efficiency.

•Sep 3, 2026•0 citations
The development of credit scoring models holds significant importance in banking for crediting operations. Combining multiple credit scoring models using a stacking generalization approach often yields improved results. However, selecting the optimal combination of credit scoring models is NP-Hard. In recent years, emerging quantum annealing (QA) techniques have shown promise in the field of combinatorial optimization and are considered potential solutions for NP-Hard problems. Hence, we propose an approach that employs QA for solving the credit scoring model combination optimization problem using a stacking generalization approach. By employing both auxiliary variable substitution and polynomial reduction methods, two distinct Quadratic Unconstrained Binary Optimization (QUBO) models suitable for quantum annealing are formulated. Experimental results demonstrate that the hybrid quantum annealing solver outperforms simulated annealing and simulated quantum annealing in terms of optimization capability across various problem sizes. The polynomial reduction and auxiliary variable substitution methods each exhibit their own advantages in terms of solution quality and computational efficiency.
In the context of business such as bank credit cards or related loans, banks score customers through credit scoring cards. Loan interest income and bad debt losses determined by the combination of thresholds of different credit scoring cards are key factors that determine the bank's final income. This paper mainly studies the combination optimization of credit scoring cards by establishing an optimization model and transforming it into a Quadratic Unconstrained Binary Optimization (QUBO) problem. First, the optimization problem of a single credit scoring card is studied, the data is preprocessed and zero-one integer programming model is established, then convert the objective function into a Hamiltonian to obtain an optimization model in the form of QUBO, and obtain the maximum bank income and the threshold of a single credit scoring card through the Simulated Annealing. Then, the credit scoring card combination optimization problem is studied. On the basis of the above research, variable substitution is used to reduce function degree, and a penalty function is introduced to obtain an unconstrained QUBO model for the combination problem. The D-Wave quantum annealing algorithm is used to obtain the optimal combination solution.
Credit cards are a rule by which banks rate their customers. Different credit scoring cards have different thresholds, corresponding to different pass rates and bad debt rates, which have a crucial impact on the bank's revenue. To help banks choose the best combination of credit scoring cards, so as to maximize revenue. Based on the triple credit card combination strategy of the bank, this paper establishes a mathematical programming model for solving the optimal combination. Aiming at the particularity of the binary decision variables, a constraint method is proposed to transform the quartic and quartic terms in the model into quadratic terms. Then, in order to balance the relationship between the objective function and the constraint conditions, the weighted penalty coefficient is further introduced by combining the entropy weight method. The model is transformed into QUBO(quadratic unconstrained binary optimization) model, and then combined with the bank's credit score card data, the optimal combination is solved by quantum annealing algorithm and verified by experiment. The experimental results show that this method has high precision and strong applicability in solving combinatorial optimization problems.
With the development of the times, the usage of loan-related business is increasing. However, most of the credit score card portfolio methods used nowadays are manually designed and supplemented with computer calculations, so the bank yields are low. Therefore, it is of great interest to study the application of quantum computers in credit score card portfolio optimization for better rating of customer credit ratings. Based on the given credit score card data, a linear programming model is developed. Firstly, the data is processed into two sets of one-dimensional data by Python and the working range of the two sets of data is found. Secondly, after deriving the objective function expressions according to the given conditions, the data were visualized by building a 3D grid matrix with the pass rate and bad debt rate as the XOY plane and the final benefit to the bank as the Z axis. Subsequently, the decision variables in the linear programming model are converted into binary variables, and the original model is transformed into a QUBO model by converting the constraints into binary variables. After analyzing the QUBO model, the quantum annealing method is chosen to solve the optimal solution of the objective function. And based on this, the case of three selected credit score card combinations and any three credit score cards are considered.
Recent advances in quantum computing have shown great potential for solving combinatorial optimization problems. A notable example is the quadratic knapsack problem, a constrained binary optimization problem. However, current quantum-inspired algorithms require Quadratic Unconstrained Binary Optimization (QUBO) formulations. Transforming constrained optimization into QUBO impacts the algorithms' speed and efficiency. In this study, we evaluate five existing transformation methods and propose four novel approaches. We assess them by using Simulated Annealing (SA), and find that three of our approaches outperform existing methods in terms of execution time as well as quality and quantity of feasible solutions found. Also, we tested these transformations on a quantum annealer, which was unable to solve even small instances, due to limitations in connectivity and error rates. In general, our results highlight the advantages of the new approaches, which reduce the number of variables in the QUBO representation.
The country's lending modality has long been credit lending. In reality, banks originate multiple portfolios. Therefore, it is necessary to build a model to select an appropriate portfolio to maximize the final return of the bank. Quantum annealing algorithm is an optimization algorithm based on quantum computing, which can be used to solve complex optimization problems, evaluate the risk of different portfolios, and help investors to identify the potential risks and take appropriate measures. In this paper, the threshold information of 100 credit cards is collected, and each credit card corresponds to 10 thresholds. This paper tries to find the maximum 3 credit card threshold portfolio of bank loan income, so it establishes an optimization model, introduces 0-1 variables, establishes an objective income function to the QUBO model, and runs 10 times the premise to get the final portfolio of the highest income credit card thresholds through the quantum annealing algorithm. Finally, combining the results of the operation of the simulated annealing model, the speed and accuracy of the operation of the quantum ventilation is found.
This paper explores the application of Quantum Annealing (QA) to the field of combinatorial optimization. The core idea is to leverage the principles of quantum mechanics, specifically quantum tunneling, to efficiently solve complex optimization problems. We present a framework for utilizing QA to tackle problems represented as quadratic unconstrained binary optimization (QUBO) models. The methodology focuses on mapping the problem's constraints and objective function into a form suitable for QA hardware. We discuss the challenges involved in this mapping process, including the limitations of current QA devices and the need for careful problem formulation. Furthermore, we analyze the potential advantages of QA over classical optimization techniques, particularly concerning the exploration of a wider solution space. The research highlights the promise of QACO as a viable approach for tackling computationally demanding combinatorial optimization tasks, offering a novel method to enhance optimization efficiency.