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 Intelligent Computing and Robotics (ICICR)

Enterprise Portfolio Optimization Based on Particle Swarm Optimization and Quantum Approximate Optimization Algorithm

Aiqing Wang, Qing Zhou

Published May 16, 2025• 2 citations
Publisher

Abstract

With the development of intelligent algorithms, new challenges have emerged in the financial field in optimizing the investment portfolio. In view of the current problems existing in portfolio optimization, the particle swarm algorithm (Particle Swarm Optimization, PSO) and quantum approximation optimization algorithm (Quantum Approximate Optimization Algorithm, QAOA) of the initial population Qanta coding is improved, and a hybrid algorithm suitable for solving enterprise portfolio optimization problems is proposed. The results found that the average performance of this method is below 0.06, which is better compared with the comparison algorithm. At the same time, with the increase of the risk level, the maximum, minimum and average increase of the yield are $10.99 \%, 19.80 \%$ and 7.98% respectively, stabilizing. The results show that the research algorithm is effective in solving the enterprise portfolio optimization problem, has better optimization ability in practical application, and can provide reference for enterprise investors to make investment decisions.

DOI
10.1109/icicr65456.2025.00119

Related papers

Quantum alternating operator ansatz with PSO optimizer for portfolio optimization problem

Wenjie Liu, Yue Ma, Yuchen Gu +2 more

Recently, Quantum Approximate Optimization Algorithm (QAOA) and Quantum Alternating Operator ansatz (QAOAz) are utilized to solve the Mean Variance (MV) model for the portfolio optimization problem (QAOAz-MV), which shows performance advantages over classical algorithms on this huge search space. For the more complex and comprehensive risk parity (RP) model, a novel QAOAz solution (QAOAz-RP) is proposed. We begin by defining the RP model for the portfolio optimization problem. Next, we detail the QAOAz algorithm process, where the problem Hamiltonian with the ZZZZ term is derived, the corresponding quantum circuit is ingeniously constructed using the parity check method, and the whole quantum circuit containing the ring XY-mixer is given. Finally, to improve the optimization performance of QAOAz, a Particle Swarm Optimization (PSO) optimizer is introduced to tune the parameters of the quantum circuits, which is applicable to both QAOAz-MV and QAOAz-RP. The experiment conducted on multiple financial markets (e.g. Chinese, U.S., and European) demonstrate that PSO-QAOAz-RP is significantly better for portfolio optimization than ABC-LP, GWO, GA and QAOAz-RP on eight portfolios in all metrics. PSO-QAOAz-MV also has advantage for MV model over the quantum algorithms, including QAOA (improves approximate ratio by 54.79% on average) and QAOAz (improves approximate ratio by 15.38% on average). This study not only provides a breakthrough quantum solution for portfolio optimization, but also provides a reusable technology paradigm for the deep integration of quantum computing and financial engineering. • It is the first QAOAz solution for the RP model of portfolio optimization problem. • The problem Hamiltonian and quantum circuit are derived and ingeniously constructed. • A PSO optimizer is proposed to optimize the parameters of QAOAz’s quantum circuit. • Our QAOAz-RP and PSO-QAOAz-RP outperform state-of-the-art classical algorithms. • Our PSO optimizer is effective on both MV and RP models.

Applied Soft Computing•Jun 14, 2025•1 citation

Quantum Approximate Optimization Algorithm for Large-Scale Portfolio Selection with Multi-Factor Constraints

Deni Teminyan

Large-scale portfolio optimization is hard because investors must balance risk, return, diversification, and liquidity across many assets with complex constraints. Classical methods, such as quadratic programming or metaheuristics, often become slow or less effective as the number of assets and factors grows. In this project, I explore the use of the Quantum Approximate Optimization Algorithm (QAOA) as a hybrid quantum–classical approach to portfolio selection. The framework encodes portfolio decisions as qubits and represents financial objectives—such as mean–variance trade-offs or risk-adjusted return—inside a parameterized quantum circuit. Classical optimization is then used to tune the circuit parameters so that the quantum system converges toward low-risk, high-return portfolios. Multi-factor constraints, including sector limits, liquidity rules, ESG scores, and macroeconomic risk factors, are integrated into the Hamiltonian as penalty terms. A qualitative comparison with classical solvers (e.g., mixed-integer programming and simulated annealing) suggests that QAOA can scale more gracefully in high-dimensional settings and handle complex constraint structures. Overall, the project shows how quantum hybrid optimization could support future portfolio management, linking theoretical quantum algorithms with practical, sustainability-aware investment strategies.

Next generation.•Nov 16, 2025•0 citations

Quantum Ensemble Optimisation: Revolutionizing Investment Portfolio Management with QAOA and VQE Integration

Yash Shah, Nitesh Bhalala, Pankaj Sonawane +3 more

Quantum computing is presenting promising prospects for financial applications, specifically in the domain of investment portfolio management. The present study investigates the capabilities of Quantum Ensemble Optimisation (QEO), an approach that integrates the Variational Quantum Eigensolver (VQE) and the Quantum Approximate Optimisation Algorithm (QAOA). Enhancing portfolio performance through a balance between diversification and risk-adjusted returns is our objective. A novel methodology has been devised to integrate the flexibility of VQE with the efficacy of QAOA, yielding an assortment of portfolio solutions. Our investigation into the performance of our model on empirical financial data has revealed that it surpasses conventional optimization techniques in terms of risk-adjusted returns and solution space exploration. The results of this study underscore the potential of our hybrid methodology, which capitalizes on the advantages of QAOA and VQE, to propel the field of quantum-based portfolio optimization forward. This may ultimately result in investors reaching more informed investment decisions and experiencing enhanced financial outcomes.

Educational Administration Theory and Practice journal•Jan 8, 2024•0 citations

Quantum Algorithms for Financial Optimization: Benchmarking QAOA, VQE, and Classical Portfolio Techniques

Subodh Nath Pushpak, Sonal Jain, Siddharth Kalra

Portfolio optimization is a fundamental problem in quantitative finance that seeks to maximize risk-adjusted returns while managing investment risk. With the advent of quantum computing, there is growing interest in applying quantum algorithms to solve complex optimization problems. This paper presents a comprehensive comparative study of quantum and classical approaches to portfolio optimization, specifically comparing the Quantum Approximate Optimization Algorithm (QAOA), Variational Quantum Eigensolver (VQE), and classical mean-variance optimization. We evaluate these methods on both real market data and synthetic datasets with varying correlation structures. Our experimental results show that while classical methods currently outperform quantum approaches on near-term quantum devices in terms of solution quality and computational efficiency, quantum algorithms demonstrate conceptual viability and promise for future applications as quantum hardware improves. The classical method achieves optimal Sharpe ratios of 1.2-1.8, while QAOA and VQE achieve 80-95% and 75-90% of classical performance respectively. This work provides insights into the current state and future potential of quantum computing for financial optimization.

International Conference on Innovative Practices in Technology and Management (ICIPTM)•Feb 19, 2026•0 citations

A Two-Step Quantum Approximate Optimization Algorithm for Portfolio Optimization and Risk Assessment

Boxuan Wu, Lei Wang

Quantum finance represents a pivotal and cutting-edge application domain within the burgeoning field of quantum computing. In this work, we propose a two-step quantum approximate optimization algorithm (two-step QAOA) for portfolio optimization and risk assessment. The algorithm initiates by formulating the stock selection problem as a quadratic unconstrained binary optimization (QUBO) problem and employs a classical-quantum hybrid method to find the ground state of the Hamiltonian. We then introduce an energy-based characteristic indicator U∈[0,1), which quantitatively evaluates portfolio performance under customizable investment preferences, effectively capturing the trade-off between expected return and risk. The number of qubits required scales with the number of stocks N in the pool, and the number of Hamiltonian terms is O(N2). Numerical simulations show that the algorithm provides consistent and reasonable assessment results on both training and test datasets under different investment preferences (aggressive or conservative), validating the capability of the characteristic indicator to extract intrinsic information from the portfolios. Additionally, by incorporating warm-starting and digitized counterdiabatic techniques, the algorithm achieves improved scalability and faster convergence. Our work presents a flexible and practical algorithmic framework for applying quantum computing in the financial domain.

Quantum Reports•May 7, 2026•0 citations

PO-QA: A Framework for Portfolio Optimization using Quantum Algorithms

Kamila Zaman, Alberto Marchisio, Muhammad Kashif +1 more

Portfolio Optimization (PO) is a financial problem aiming to maximize the net gains while minimizing the risks in a given investment portfolio. The novelty of Quantum algorithms lies in their acclaimed potential and capability to solve complex problems given the underlying Quantum Computing (QC) infrastructure. Utilizing QC's applicable strengths to the finance industry's problems, such as PO, allows us to solve these problems using quantum-based algorithms such as Variational Quantum Eigensolver (VQE) and Quantum Approximate Optimization Algorithm (QAOA). While the Quantum potential for finance is highly impactful, the architecture and composition of the quantum circuits have not yet been properly defined as robust financial frameworks/algorithms as state of the art in present literature for research and design development purposes. In this work, we propose a novel scalable framework, denoted PO-QA, to systematically investigate the variation of quantum parameters (such as rotation blocks, repetitions, and entanglement types) to observe their subtle effect on the overall performance. In our paper, the performance is measured and dictated by convergence to similar ground-state energy values for resultant optimal solutions by each algorithm variation set for QAOA and VQE to the exact eigensolver (classical solution). Our results provide effective insights into comprehending PO from the lens of Quantum Machine Learning in terms of convergence to the classical solution, which is used as a benchmark. This study paves the way for identifying efficient configurations of quantum circuits for solving PO and unveiling their inherent inter-relationships.

arXiv:2407.19857•IEEE International Conference on Quantum Computing and Engineering (QCE)•Sep 15, 2024•12 citations
With the development of intelligent algorithms, new challenges have emerged in the financial field in optimizing the investment portfolio. In view of the current problems existing in portfolio optimization, the particle swarm algorithm (Particle Swarm Optimization, PSO) and quantum approximation optimization algorithm (Quantum Approximate Optimization Algorithm, QAOA) of the initial population Qanta coding is improved, and a hybrid algorithm suitable for solving enterprise portfolio optimization problems is proposed. The results found that the average performance of this method is below 0.06, which is better compared with the comparison algorithm. At the same time, with the increase of the risk level, the maximum, minimum and average increase of the yield are 10.99%,19.80%10.99 \%, 19.80 \%10.99%,19.80% and 7.98% respectively, stabilizing. The results show that the research algorithm is effective in solving the enterprise portfolio optimization problem, has better optimization ability in practical application, and can provide reference for enterprise investors to make investment decisions.
Recently, Quantum Approximate Optimization Algorithm (QAOA) and Quantum Alternating Operator ansatz (QAOAz) are utilized to solve the Mean Variance (MV) model for the portfolio optimization problem (QAOAz-MV), which shows performance advantages over classical algorithms on this huge search space. For the more complex and comprehensive risk parity (RP) model, a novel QAOAz solution (QAOAz-RP) is proposed. We begin by defining the RP model for the portfolio optimization problem. Next, we detail the QAOAz algorithm process, where the problem Hamiltonian with the ZZZZ term is derived, the corresponding quantum circuit is ingeniously constructed using the parity check method, and the whole quantum circuit containing the ring XY-mixer is given. Finally, to improve the optimization performance of QAOAz, a Particle Swarm Optimization (PSO) optimizer is introduced to tune the parameters of the quantum circuits, which is applicable to both QAOAz-MV and QAOAz-RP. The experiment conducted on multiple financial markets (e.g. Chinese, U.S., and European) demonstrate that PSO-QAOAz-RP is significantly better for portfolio optimization than ABC-LP, GWO, GA and QAOAz-RP on eight portfolios in all metrics. PSO-QAOAz-MV also has advantage for MV model over the quantum algorithms, including QAOA (improves approximate ratio by 54.79% on average) and QAOAz (improves approximate ratio by 15.38% on average). This study not only provides a breakthrough quantum solution for portfolio optimization, but also provides a reusable technology paradigm for the deep integration of quantum computing and financial engineering. • It is the first QAOAz solution for the RP model of portfolio optimization problem. • The problem Hamiltonian and quantum circuit are derived and ingeniously constructed. • A PSO optimizer is proposed to optimize the parameters of QAOAz’s quantum circuit. • Our QAOAz-RP and PSO-QAOAz-RP outperform state-of-the-art classical algorithms. • Our PSO optimizer is effective on both MV and RP models.
Large-scale portfolio optimization is hard because investors must balance risk, return, diversification, and liquidity across many assets with complex constraints. Classical methods, such as quadratic programming or metaheuristics, often become slow or less effective as the number of assets and factors grows. In this project, I explore the use of the Quantum Approximate Optimization Algorithm (QAOA) as a hybrid quantum–classical approach to portfolio selection. The framework encodes portfolio decisions as qubits and represents financial objectives—such as mean–variance trade-offs or risk-adjusted return—inside a parameterized quantum circuit. Classical optimization is then used to tune the circuit parameters so that the quantum system converges toward low-risk, high-return portfolios. Multi-factor constraints, including sector limits, liquidity rules, ESG scores, and macroeconomic risk factors, are integrated into the Hamiltonian as penalty terms. A qualitative comparison with classical solvers (e.g., mixed-integer programming and simulated annealing) suggests that QAOA can scale more gracefully in high-dimensional settings and handle complex constraint structures. Overall, the project shows how quantum hybrid optimization could support future portfolio management, linking theoretical quantum algorithms with practical, sustainability-aware investment strategies.
Quantum computing is presenting promising prospects for financial applications, specifically in the domain of investment portfolio management. The present study investigates the capabilities of Quantum Ensemble Optimisation (QEO), an approach that integrates the Variational Quantum Eigensolver (VQE) and the Quantum Approximate Optimisation Algorithm (QAOA). Enhancing portfolio performance through a balance between diversification and risk-adjusted returns is our objective. A novel methodology has been devised to integrate the flexibility of VQE with the efficacy of QAOA, yielding an assortment of portfolio solutions. Our investigation into the performance of our model on empirical financial data has revealed that it surpasses conventional optimization techniques in terms of risk-adjusted returns and solution space exploration. The results of this study underscore the potential of our hybrid methodology, which capitalizes on the advantages of QAOA and VQE, to propel the field of quantum-based portfolio optimization forward. This may ultimately result in investors reaching more informed investment decisions and experiencing enhanced financial outcomes.
Portfolio optimization is a fundamental problem in quantitative finance that seeks to maximize risk-adjusted returns while managing investment risk. With the advent of quantum computing, there is growing interest in applying quantum algorithms to solve complex optimization problems. This paper presents a comprehensive comparative study of quantum and classical approaches to portfolio optimization, specifically comparing the Quantum Approximate Optimization Algorithm (QAOA), Variational Quantum Eigensolver (VQE), and classical mean-variance optimization. We evaluate these methods on both real market data and synthetic datasets with varying correlation structures. Our experimental results show that while classical methods currently outperform quantum approaches on near-term quantum devices in terms of solution quality and computational efficiency, quantum algorithms demonstrate conceptual viability and promise for future applications as quantum hardware improves. The classical method achieves optimal Sharpe ratios of 1.2-1.8, while QAOA and VQE achieve 80-95% and 75-90% of classical performance respectively. This work provides insights into the current state and future potential of quantum computing for financial optimization.
Quantum finance represents a pivotal and cutting-edge application domain within the burgeoning field of quantum computing. In this work, we propose a two-step quantum approximate optimization algorithm (two-step QAOA) for portfolio optimization and risk assessment. The algorithm initiates by formulating the stock selection problem as a quadratic unconstrained binary optimization (QUBO) problem and employs a classical-quantum hybrid method to find the ground state of the Hamiltonian. We then introduce an energy-based characteristic indicator U∈[0,1), which quantitatively evaluates portfolio performance under customizable investment preferences, effectively capturing the trade-off between expected return and risk. The number of qubits required scales with the number of stocks N in the pool, and the number of Hamiltonian terms is O(N2). Numerical simulations show that the algorithm provides consistent and reasonable assessment results on both training and test datasets under different investment preferences (aggressive or conservative), validating the capability of the characteristic indicator to extract intrinsic information from the portfolios. Additionally, by incorporating warm-starting and digitized counterdiabatic techniques, the algorithm achieves improved scalability and faster convergence. Our work presents a flexible and practical algorithmic framework for applying quantum computing in the financial domain.
Portfolio Optimization (PO) is a financial problem aiming to maximize the net gains while minimizing the risks in a given investment portfolio. The novelty of Quantum algorithms lies in their acclaimed potential and capability to solve complex problems given the underlying Quantum Computing (QC) infrastructure. Utilizing QC's applicable strengths to the finance industry's problems, such as PO, allows us to solve these problems using quantum-based algorithms such as Variational Quantum Eigensolver (VQE) and Quantum Approximate Optimization Algorithm (QAOA). While the Quantum potential for finance is highly impactful, the architecture and composition of the quantum circuits have not yet been properly defined as robust financial frameworks/algorithms as state of the art in present literature for research and design development purposes. In this work, we propose a novel scalable framework, denoted PO-QA, to systematically investigate the variation of quantum parameters (such as rotation blocks, repetitions, and entanglement types) to observe their subtle effect on the overall performance. In our paper, the performance is measured and dictated by convergence to similar ground-state energy values for resultant optimal solutions by each algorithm variation set for QAOA and VQE to the exact eigensolver (classical solution). Our results provide effective insights into comprehending PO from the lens of Quantum Machine Learning in terms of convergence to the classical solution, which is used as a benchmark. This study paves the way for identifying efficient configurations of quantum circuits for solving PO and unveiling their inherent inter-relationships.