The objective of this research was to apply near-infrared spectroscopy, with a short-wavelength range of 950 to 1,650 nm, for the rapid detection of aflatoxin B (AFB) contamination in polished rice samples. Spectra were obtained by reflection mode for 105 rice samples: 90 samples naturally contaminated with AFB and 15 samples artificially contaminated with AFB. Quantitative calibration models to detect AFB were developed using the original and pretreated absorbance spectra in conjunction with partial least squares regression with prediction testing and full cross-validation. The statistical model from the external validation process developed from the treated spectra (standard normal variate and detrending) was most accurate for prediction, with a correlation coefficient () of 0.952, a standard error of prediction of 3.362 μg/kg, and a bias of -0.778 μg/kg. The most predictive models according to full cross-validation were developed from the multiplicative scatter correction pretreated spectra ( = 0.967, root mean square error in cross-validation [RMSECV] = 2.689 μg/kg, bias = 0.015 μg/kg) and standard normal variate pretreated spectra ( = 0.966, RMSECV = 2.691 μg/kg, bias = 0.008 μg/kg). A classification-based partial least squares discriminant analysis model of AFB contamination classified the samples with 90% accuracy. The results indicate that the near-infrared spectroscopy technique is potentially useful for screening polished rice samples for AFB contamination.