The purpose of this study is to evaluate the potential of fluorescence spectroscopy to predict the nutritional parameters of twenty-six commercially available wheat flours from different vendors. Principal component analysis (PCA) was used to clearly identify the correlations among different types of flours. A partial least square regression (PLSR) model gives a good prediction for moisture, fat and carbohydrates using cross-validation, with a R 2 of 0.86, 0.88 and 0.89 respectively. However, the protein, sucrose and salt contents showed little correlation in PLSR. Locally weighted regression (LWR) provides a significant improvement in the prediction of all of the nutritional parameters. The error decreases with an increasing R 2 to 0.96, 0.93, 0.99, 0.98, 0.99, 0.88, 0.95 and 0.99 for the energetic value, protein, fat, moisture, carbohydrate, sucrose, salt and saturated fatty acid contents respectively, for different wheat flours. Hence, fluorescence, which is a non-invasive and rapid method, can be used to evaluate the nutritional parameters of different types of wheat flours. Estimation of nutritional parameters M. H. Ahmad et al. † Flour type 405 contains less than 0.5% mineral contents. ‡ Flour type 550 contains 0.5-0.63% mineral contents. § Flour type 1050 contains 0.91-1.2% mineral contents. ¶ Whole wheat flour contains 1.2-1.8% mineral contents. Estimation of nutritional parameters M. H. Ahmad et al. † Root mean square error of cross-validation. ‡ Coefficient of determination for cross-validation. Estimation of nutritional parameters M. H. Ahmad et al. † Root mean square error of cross-validation. ‡ Coefficient of determination for cross-validation. Estimation of nutritional parameters M. H. Ahmad et al.