There has been a growing interest in the development of advanced methodologies aimed at estimating the optimal individualized treatment rules (ITR) in various fields, such as business decision making, precision medicine, and social welfare distribution. The application of individualized treatment rules (ITR) within a societal context raises substantial concerns regarding the potential for unintended discrimination. Customized policies learned from biased data can inadvertently lead to disparities based on sensitive attributes such as age, gender, or race. To address this concern directly, we introduce a tailored nonlinear fairness constraint that aligns with the requirements of demographic parity (DP) ITR. We obtain the optimal demographic parity-aware ITR solution by solving a non-convex constrained optimization problem. To overcome computational challenges, we identify linear and nonlinear fairness constraint proxies and leverage the support vector machine framework to transform it into a convex quadratic programming problem. Additionally, we establish the asymptotic consistency and convergence rate of the proposed estimator. We demonstrate performance of the proposed method through extensive simulation studies and a real data analysis utilizing the entrepreneurial program data.