In this paper Extreme Gradient Boost (XGBoost) based machine learning model is designed to predict the critical buckling load of near-spherical composite shells (Icosahedron). Icosahedron is under external pressure, and the effect of changing the geometry or the composite layups on the buckling load is studied in this paper. While designing a composite structure, the engineering design space is often very large. Finding possible combinations to obtain the higher buckling load could be time consuming and computationally expensive. To overcome this problem, a data-driven machine learning model is created in this paper based on the data generated from detailed finite element analyses. Based on the geometry design parameters or material design parameters, the current model predicts the buckling load with excellent accuracy. To verify and test the model an independent test data set is created for each case and then the correlation value (R2 value) or average Root Mean Square Error (RMSE) is computed.