The electrochemical conversion of CO2 into useful chemicals in a microfluidic flow cell (MFC) reactor depends not only on intrinsic electrochemical, physical, and material parameters but also on extrinsic operating conditions and cell design. Variations in these parameters significantly affect the overall performance of the MFC reactor. In this regard, to correlate the cell performance, conversion efficiency, and selectivity of the MFC reactor with the variability of these input parameters, we carry out a Monte Carlo simulation (MCS) based on a mechanistic mathematical model for the electrochemical conversion of CO2 to CO. The MCS is conducted in two scenarios: first, by varying the stochastic parameters individually (IND), and second, by varying all of the stochastic parameters simultaneously (SIM), at different cell potentials. These parameters are then ranked on the basis of their contributions to the cell performance, the conversion efficiency, and the selectivity, thereby providing insights into optimum ranges of operation. The charge-transfer coefficient toward CO and H-2 formation, catalyst properties, are the most sensitive parameters toward the cell performance and conversion efficiency and the selectivity, respectively, at all cell potentials. The thickness of the catalyst layer has a significant effect on the cell performance and conversion efficiency during the IND scenario, but its relative effect during the SIM scenario is not significant at all cell potentials. Furthermore, we derive reduced regression models based on supervised machine learning algorithms to predict the overall cell performance without having to solve the complete set of equations and also statistically discuss the distribution of overall cell performance at various cell potentials.