The resistance mutations EGFR in epidermal growth factor receptor (EGFR) are key factors in the reduced efficacy of Osimertinib. Predicting the inhibitory effects of Osimertinib derivatives against these mutations is crucial for the development of more effective inhibitors. This study aims to predict the inhibitory effects of Osimertinib derivatives against EGFR mutations. Six models were established using heuristic method (HM), random forest (RF), gene expression programming (GEP), gradient boosting decision tree (GBDT), polynomial kernel function support vector machine (SVM), and mixed kernel function SVM (MIX-SVM). The descriptors for these models were selected by the heuristic method or XGBoost. Comprehensive learning particle swarm optimizer was adopted to optimize hyperparameters. Additionally, the internal and external validation were performed by leave-one-out cross-validation (QLOO2), 5-fold cross validation (Q5-fold2) and concordance correlation coefficient (CCC), QF12, and QF22. The properties of novel EGFR inhibitors were explored through molecular docking analysis. The model established by MIX-SVM whose kernel function is a convex combination of three regular kernel functions is best: R2 and RMSE for training set and test set are 0.9445, 0.1659 and 0.9490, 0.1814, respectively; QLOO2, Q5-fold2, CCC, QF12, and QF22 are 0.9107, 0.8621, 0.9835, 0.9689, and 0.9680. Based on these results, the IC values of 162 newly designed compounds were predicted using the HM model, and the top four candidates with the most favorable physicochemical properties were subsequently validated through PEA. The MIX-SVM method will provide useful guidance for the design and screening of novel EGFR inhibitors.