Conventional household refrigerators consist of a motor-driven compressor, evaporator, condenser, and expansion valve. To determine the optimal operation strategies of refrigerators, it is essential to investigate the overall system performance, using an appropriate simulator. This study proposed a data-driven simulator based on engineering features and machine learning algorithms for conventional household refrigerators. The most correlated variables for identifying the indoor temperature of refrigerators were identified using variable importance, and these were revealed to be the circulation fan speed, compressor operation status, and refrigerant flow direction. A data-driven simulator was constructed using Bayesian calibration, which considers the important variables, combined with a straightforward heat balance equation. The Markov Chain Monte Carlo approach was used to simultaneously calibrate three coefficients on the critical variables based on the heat balancing equation on each time step, which is consistent with the actual temperature of the container. The results revealed that the proposed approach (equation-based Bayesian calibration outperforms) standard machine learning algorithms, such as linear regression and random forest models, by 38.5%. Additionally, compared to the typical numerical analysis method, it can reduce the delivery time and effort required to develop a reliable simulator for household refrigerators.