To achieve the rapid determination of gentamicin (GM) in duck egg white and improve the accuracy of prediction model,the optimized characteristic spectral wavelengths are extract ed from derivative synchronous fluorescence spectrum using genetic algorithm (GA),and the prediction model of G M contents in duck egg white is developed by using GA-support vector regression (GA- SVR).Firstly,3-D synchronous fluorescence spectra of samples are analyzed and 120nm is selected as the opt imum wavelength difference in this paper.Secondly,the noise of the first order derivative synchronous spectrum is reduced by using the sym5wavelet with 2decompositions,and 14characteristic wavelengths are selected by using GA.Lastly,the parameters (c,g,p) of RBF kernel function are optimized by using GA.Furthermore,the performance of 3models of GA-SVR,PLS and MLR is compared,and the best prediction results are o btained by using the GA-SVR model.The experimental results show that the determination coefficient ( R² ) and the root mean squared error of prediction (RMSEP) for the GA-SVR model are 0.9830and 1.1494mg/L,respectively.This w ork proves that GA could effectively extract characteristic spectral wavelengths to determi ne the gentamicin content in duck egg white and improve the prediction accuracy of the GA-SVR model.