The ability of obtaining soil properties estimations from time and cost efficient remotely sensed techniques has been identified as a valuable technique as there is a great demand for larger amounts of good quality and inexpensive soil data to be used in environmental monitoring, modelling and precision agriculture. Visible (Vis) and Near Infrared (NIR) spectroscopy provides a good alternative that may be used to enhance or replace conventional methods of soil analysis. The aim of this paper is to evaluate the abilities of Vis (350-700 nm) and near infrared (700-2500 nm) for prediction of soil nutrients. In this instance we implemented Savitzky-Golay algorithm and Stepwise Multiple Linear Regression (SMLR) to construct calibration models. The soil nutrients examined were soil Total Nitrogen (N), Available Phosphorus (P) and Exchangeable Potassium (K). Our results revealed the accuracy of SMLR prediction in each of the Vis and NIR spectral regions. The NIR produced more accurate predictions for N and K; however, higher significant correlation was obtained using the Vis for available P. This work demonstrated Vis and NIR spectroscopy could be considered as a good tool to assess soil nutrients in Malaysian paddy fields.