The geographical origin of Chinese ginseng is of great concern to customers, since quality varies tremendously with geographical origin. Therefore, accurately distinguishing the region of origin of specific types of ginseng, in order to differentiate the quality, is of great significance. In this paper, MPT-AES integrated with support vector machine (SVM) was proposed and applied to determine and classify the geographical origin of ginseng samples by using the chemical elemental compositions obtained. Specific data sets were extracted and dimensions were reduced through wavelet transformation. A classification model was built, relying on training sets, and then two parameters (c and g) were optimized in the SVM approach. SVM and Gaussian process classification (GPC) models were evaluated entirely on their prediction accuracy for unknown ginseng samples. Under optimized conditions, SVM outperformed GPC with a prediction accuracy of 100%, compared to 97.41%, in distinguishing the geographical origins. SVM also proved valid in the classification of individual types of ginseng with 99.81% accuracy, compared to GPC with 71.67%. These advanced chemometrics worked well for American ginseng identification. This study illustrates that chemometrics, together with the MPT-AES spectrochemical method, is a helpful and innovative technique for identifying and classifying ginseng samples, and is promising for accurate, convenient, automatic and reliable analysis.