Machine learning has become an emerging method for next-generation smart technologies. It also promotes a development-paradigm shift in sensing technologies, which are essential in various smart applications. In this work, we develop a data-driven method for a monolithic ion-sensitive field-effect transistor (ISFET) to have both photon and pH bi-detection capabilities simultaneously. The proposed methods are executed based on sequential-bias-reconfiguration of the ISFET. Utilizing support vector machine and back-propagation neural network, the photocurrent and ion-induced current can be calculated and decoupled. To evaluate the proposed method, semi-quantification by classification methods and quantification by regression methods are both examined. This work has experimentally demonstrated the dual-detection capability of a pH range from 5 to 9 and an intensity range from 0 to 760 lW/cm2 with prediction error less than 1.5%. To fulfill low-computation requirement for applications, we further optimize the proposed algorithm by feature reduction to balance performances between accuracy, complexity of data acquisition, and data processing. With the developed machine-learning sensing device, therefore, we successfully demonstrate potentials of data-driven sensing devices in future applications.