This research presents a soft computing methodology for groutability estimation of grouting processes that employ cement grouts. The method integrates a hybrid metaheuristic and the Support Vector Machine (SVM) with evolutionary input factor and hyper-parameter selection. The new prediction model is constructed and verified using two datasets of grouting experiments. The contribution of this study to the body of knowledge is multifold. First, the efficacies of the Flower Pollenation Algorithm (FPA) and the Differential Evolution (DE) are combined to establish an integrated metaheuristic approach, named as Differential Flower Pollenation (DFP). The integration of the FPA and the DE aims at harnessing the strength and complementing the disadvantage of each individual optimization algorithm. Second, the DFP is employed to optimize the input factor selection and hyper-parameter tuning processes of the SVM-based groutability prediction model. Third, this study conducts a comparative work to investigate the effects of different evaluation functions on the model performance. Finally, the research findings show that the new integrated framework can help identify a set of relevant groutability influencing factors and deliver superior prediction performance compared with other state-of-the-art approaches.