This research focused on developing a hybrid quality monitoring model through combining the data-driven and key engineering parameters to predict the friction stir blind riveting (FSBR) joint quality. The hybrid model was formulated through utilizing the in situ processing and joint property data. The in situ data involved sensor fusion (force and torque signals) and key processing parameters (spindle speed, feed rate, and stacking sequence) for data-driven modeling. The quality of the FSBR joints was defined by the tensile strength. Furthermore, the joint cross-sectional analysis and failure modes in lap shear tests were employed to confirm the efficacy of the proposed model and development of the process–structure–property relationship.