The feature compression algorithm which was reformed from the original Moment method was used for the pre-processing of the fluorescence spectral data, then combined the data and the Weighted Least Squares Support Vector Machine(WLS-SVM) algorithm to establish a robust regression model, which is used for forecasting the purity of edible pigment powder. In this paper, brilliant blue and ponceau 4R served as an example to discuss the method of forecasting effect of edible pigment powder purity. The emission fluorescence spectra of two edible pigment at the optimal excitation wavelength were measured by FLS920 fluorescence spectrometer. The compression and transformation of the fluorescence spectral data was acquired by the feature compression algorithm reformed from the Original Moment method. On the one hand the feature compression algorithm shortened the operation time, on the other hand it improved the prediction accuracy of the model. Then, the concentration prediction model was established after inputting the fluorescence spectral data pre-processed into the Weighted Least Squares Support Vector Machine. The model gave anastomotic predicted spectral data with the actual experiments of the brilliant blue and ponceau 4R, and the average coefficient of determination in the half peak width was 0.700 and 0.930 respectively. There was a good linear relationship between the predicted and the nominal concentration of the brilliant blue and ponceau 4R, and the correlation coefficients were 0.997 and 0.992 respectively. It can be concluded that, the predicted concentration of the brilliant blue and ponceau 4R powder were got the results of 61.0% and 72.3% respectively.