In order to investigate a fast and efficient method determining the freshness of bee pollen, visible and nearinfrared (VisNIR) reflectance spectroscopy with least squaressupport vector machines (LSSVM) was applied to determine storage period of bee pollen. The Camellia bee pollens stored for 4~50(47) days at room temperature were investigated. Spectra were collected by an ASD Fieldspec spectrometer as the input variables to build the LSSVM model. Results show that the prediction performance of LSSVM model is better than partial least square (PLS) and principal component regression (PCR). Its correlation coefficient of prediction set (rp) is 0.996, standard error of prediction (SEP) is 1.310, and root mean square error of prediction (RMSEP) is 1.308. It is concluded that VisNIR spectroscopy with LSSVM is a feasible method to determine the storage period of bee pollen. Moreover, the results for different storage periods were compared. It is shown that the storage periods between 11~50 can be well determined by LSSVM.