As demand grows for electric vehicles and advanced mobility technologies, developing materials for permanent magnets has become increasingly essential. Among them, SmCo-based permanent magnets are gaining attention due to their superior thermal stability compared to conventional NdFeB magnets, making them promising candidates for high-temperature motor applications. However, optimizing the magnetic properties of SmCo alloys remains challenging due to their complex phase structures and elemental interactions. In this study, we develop and optimize machine learning (ML) models to predict the saturation magnetization of SmCo permanent magnets using only composition-based descriptors. A dataset comprising various SmCo alloys was analyzed, with features extracted using Matminer and Pymatgen modules. We applied Random Forest (RF), eXtreme Gradient Boosting (XGB), and Support Vector Regression (SVR) models and compared their regression performance using R2 score and Root-mean-squared-error (RMSE). The RF model demonstrated the best generalization and prediction accuracy. To identify the most influential features, we used permutation feature importance. Further, we refined the feature set using a genetic algorithm (GA), ultimately selecting 9 key features that yielded the highest model performance (R2 = 0.963, RMSE = 4.22 emu/g). This study highlights the potential of combining machine learning with genetic optimization to accelerate the design of high-performance, thermally stable SmCo permanent magnets.