<![CDATA[Background Economic corruption remains a major challenge because it generates substantial fiscal losses, weakens institutional performance, and undermines public trust. Classical economic approaches, particularly Becker’s rational choice framework, explain corruption decisions primarily through the expected utility derived from illegal gains, the probability of detection, and the severity of punishment. Purpose This study aims to develop a Quantum Becker Model (QBM) based on Quantum Neural Networks (QNNs) to provide a quantum probabilistic representation of individual and organizational corruption decisions. Methodology The proposed model represents individual cognitive states as qubits, with their evolution controlled by parameterized quantum rotation gates. Organizational corruption contagion is represented through quantum entanglement between individual decision states. Anti-corruption policy is formulated as an optimization problem by minimizing a Hamiltonian-based social loss function using a hybrid quantum gradient descent approach. Findings Numerical simulations demonstrate that the QBM can represent nonlinear relationships between corruption decisions, detection probability, and policy interventions. The model also captures organizational corruption contagion through interactions between interconnected cognitive states, providing behavioral dynamics that are not readily represented by conventional expected-utility models. The simulation results indicate that increasing the probability of corruption detection through effective auditing and institutional transparency produces a stronger deterrence effect than relying solely on increasing the severity of sanctions. Implications The findings suggest that anti-corruption strategies should place greater emphasis on increasing the perceived and actual probability of detection through effective auditing, transparency, and institutional monitoring. . Originality The originality of this study lies in integrating Becker’s economic theory of crime with quantum machine learning through a Quantum Neural Network framework. By representing cognitive uncertainty using qubits and organizational contagion using quantum entanglement, the proposed approach offers a novel computational perspective for analyzing nonlinear corruption behavior and designing economically efficient anti-corruption policies.]]>
