Fuzzy Support Vector Machine Using Particle Swarm Optimization for High-Tech Enterprises Financing Risk Assessment

Aiming at the uncertainty of external financing environment and the fuzzy of financing risk for high-tech enterprises, fuzzy support vector machine using particle swarm optimization (PSO-FSVM) for high-tech enterprises financing risk assessment is proposed. This optimization mechanism combined the discrete PSO with the continuous-valued PSO to simultaneously optimize the input feature subset selection and the FSVM kernel parameter setting. The kernel parameters and penalty factor of fuzzy support vector machine are optimized by the particle swarm optimization. The kernel parameters and penalty factor are obtained. The high-tech enterprises financing risk dataset, which includes 395 companies´ financing records and is collected by China Construction Bank, is selected to demonstrate the effectiveness and feasibility of proposed method. Experimental results reveal that PSO-FSVM can be used as an alternative method for logistics enterprise financing risk assessment.