Abstract: Reducing sugar content is one of the important indicators for evaluating the quality of potato granules. Near-infrared (NIR) spectroscopy has been attempted to determine reducing sugar content in potato granules using near-infrared (NIR) spectroscopy combined with least squares support vector machine (LSSVM) algorithm. NIR spectra were recorded in the wavenumber range of 10 000~4 000 cm-1 at a 4 cm-1 interval. The 110 samples were divided into calibration and prediction sets in terms of their respective actual value for avoiding bias in subset division. One of every four samples was divided into the prediction set according the range of actual value in calibration set covering the range in the prediction set. The calibration set contained 83 samples, and the remaining 27 samples constituted the prediction set. Three different variable selection methods, namely the moving windows partial least square (MWPLS), MWPLS-genetic algorithm (MWPLS-GA), and MWPLS-successive projection algorithm (MWPLS-SPA), were performed comparatively to choose spectral variables associated with reducing sugar content distributions. The partial least square (PLS) models were developed with these selection spectral variables with the number of PLS components optimized according to root mean square error of cross validation (RMSECV) in the calibration set. The results derived by variable selection techniques were then compared with the performance of PLS models with new samples in the prediction set. The PLS calibration model exhibited a higher correlation coefficient of prediction (Rp) of 0.976, lower standard error of prediction (SEP) of 0.273%, and ratio of SEP and standard deviation (SDR) of 4.593, which was built using 20 spectral variables selected by the MWPLS-SPA method. Nonlinear models of the least squares support vector machine (LSSVM) were developed using different spectral variables selected by MWPLS, MWPLS-GA, and MWPLS-SPA. The main parameters of penalty factor (γ) and nuclear parameters (σ2) of the nuclear function for the radial basis function (RBF) were optimized by a two-step search method. Through comparison the performance of LSSVM models with new samples, the optimal LSSVM models for reducing sugar content were obtained with Rp of 0.984, SEP of 0.223%, and SDR of 5.62, which were developed with 20 spectral variables selected by the MWPLS-SPA method. The results indicated that: 1) the accuracy of the quantitative analysis conducted by NIR spectroscopy can be improved through appropriate wavelength selection with the MWPLS-SPA method; and 2) the implementation of LSSVM nonlinear models could predict reducing sugar content in potato granules more accurately than a linear model of PLS. It was concluded that NIR spectroscopy combined with MWPLS-SPA and LSSVM methods has significant potential to quantitatively analyze reducing sugar content in potato granules, and this real time, in situ measurement will significantly improve the efficiency of quality control and assurance.