• Dynamically weighed eggs were classified by support vector machines. • Classification was made according to the weight classes specified in Ministry of Food, Agriculture and Animal-Turkish Food Codex Egg Communique • Egg classification was determined successfully using the raw measurement data in the classification process. Today, speed in the manufacturing sector has become an important factor. Dynamic weighing systems have been developed to realize the weighing transactions speedily. In the dynamic weighing systems, the products are weighted while they are passing from on the weighing platform in motion and they can reach to desired weighing speeds in this manner. However, in the dynamic weighing systems, mechanic vibrations resulting from weighing of product in motion creates an undesired distorting effect in the measuring signal. Traditionally, the weighing weight of product at the moment it becomes stable after the signal is filtered is tried to be determined by using a method. In general, the products are classified according to definite weight categories after their weights are determined. In this study egg classification was determined successfully using the raw measurement data in the classification process with support vector machines. Purpose: In this study, classification of the dynamically weighted eggs according to the weight categories set forth in the Ministry of Food, Agriculture and Animal-Turkish Food Codex Egg Communique was realized with raw data directly by using the support vector machines. Theory and Methods: In this study, a dynamic egg weighing system was realized mechanically and electronically. By applying SVM to the data received from the system, it is ensured that the eggs are separated according to weight classes. Conventional methods in dynamic weighing systems, the measurement signal is filtered using various methods to obtain a noiseless weight signal, and then a method is applied to this signal to determine the weight value at which the measurement signal is stabilized. The weight class of the egg is determined by comparing with the values stated in this weight value egg notification. In the study, the SVM method was applied to the raw measurement signal obtained from the dynamic weighing system to classify the eggs. Results: In this study, 11 weight data from the fall of the egg to the measurement platform were applied directly to the SVM classifier without any processing. At the output of the SVM, one of the tags given according to weight classes (1, 2, 3, 4) is obtained. During the formation of SVM model, 29 egg weight data were used for training and 14 egg weight data were used in the test of the model. As a result of the test procedure, all eggs were correctly classified according to the weight group labels given. Conclusion: With the proposed method, it is possible to detect directly with the SVM without applying a pre-signal processing method to the class measurement data suitable for the weight without leaving the egg measuring platform.