Abstract: The genetic algorithm optimization of support vector machine ( SVM) parameters of near infrared spectral technology was proposed in rapid determination the original fruit juice content of apple beverage, on the basis of spectral data preprocessing methods, the parameters for SVM model were pretreated through genetic algorithms to get the optimum parameter values, and these parameter values were used in the SVM model, which was used to make raw juice content forecasting. Results showed that GA-SVM algorithm set decision coefficient was 0.9757 in prediction, the technique could be used for the rapid determination of the original fruit juice content in apple drinks.