As an informative proxy measure for a range of urbanisation and socioeconomic variables, satellite-derived night-time light data have been widely used to investigate the diverse anthropogenic activities and reveal social economy development disparities from the regional to the national scale. The new-generation night-time light data have been proven to potentially improve our understanding in the development and inequality of urban social economy due to its high spatial resolution, strong timeliness and minimal background noise. These night-time light data are derived from the visible infrared imaging radiometer suite (VIIRS) instrument with day/night band located on the Suomi National Polar-orbiting Partnership (NPP) satellite. This study proposed a hybrid model to estimate urban consumption potentiality based on the comprehensive information of human activities obtained from the VIIRS night-time light data. Our method established a flexible geographically weighted regression-based estimation model based on the residential consumption data and DN values of the VIIRS data to predict the possible consumption potentiality of other urban areas in dynamic time. The experiment conducted in Guiyang, a provincial capital in China, affirms that our model is proven to have higher accuracy compared with traditional regression models and can potentially provide guidance for improved business management and increased profit.