This study proposed an approach for continuously monitoring dissolved oxygen concentration using absorption spectroscopy with a low-cost multispectral sensor. An experimental system was built to investigate the correlation between dissolved oxygen concentration and absorbance of several wavebands in the visible and near-infrared regions. An optimized linear regression model with four wavebands at 460, 485, 585, and 900 nm gave the best prediction results with coefficient of determination and root mean square error of 0.85 and 0.68 mg/L, respectively. The experimental results demonstrated that the proposed absorption spectroscopy with a low-cost multispectral sensor has great potential for continuously monitoring dissolved oxygen concentration in water in a non-contact manner.