County independent innovation ability analysis and prediction play an important role in county economic development and improve benefit of national independent innovation system. According to the county independent innovation ability data which is large scale and imbalance, this paper presented a support vector machine (SVM) model to predict county independent innovation ability. In order to improve the discrimination precision of SVM in prediction of county independent innovation ability, a Genetic Algorithm (GA) was used to optimize SVM parameters in the solution space. The proposed GA-SVM method was compared with artificial neural network, decision tree, logistic regression and naive Bayesian classifier regarding county independent innovation ability prediction for Guanzhong urban agglomeration. The result shows that the improved SVM has the best accuracy rate, hit rate, covering rate and lift coefficient, and provides an effective measurement for county independent innovation ability classification and prediction.