In recent years, soft lattices have been considered a primary physical origin of defect tolerance in lead-halide perovskite materials, with bulk modulus serving as a key indicator of lattice "softness." In this work, we focus on cubic perovskites and construct a dataset of bulk moduli for 213 compounds based on DFT calculations. A total of 138 features were compiled, including 132 statistical features extracted using the Matminer toolkit and 6 manually selected elemental descriptors. Four conventional machine learning regression models (RF, SVR, KRR, and EXR) were employed for prediction, among which the SVR model showed the best performance, achieving a test-set RMSE of 7.35 GPa and R² of 97.86%. Feature importance analysis revealed that thermodynamic-structural features such as melting point, covalent radius, and atomic volume play dominant roles in determining bulk modulus. Based on the 12 most important features, a thermodynamic-structural coupling descriptor was constructed using the SISSO method, yielding a test-set RMSE of 7.41 GPa and R² of 97.80%. The resulting descriptor indicates that bulk modulus is proportional to melting point and inversely proportional to atomic volume. Furthermore, the VS-SISSO method was applied by incorporating a random subset selection and iterative variable screening strategy, enabling the selection of electronic-level features such as electronegativity, valence state, and number of unpaired electrons. The resulting electronic-thermodynamic-structural coupling descriptor further improved prediction accuracy, reaching an RMSE of 5.34 GPa and R² of 98.35% on the test set. Notably, this model effectively distinguishes chalcogen-based (divalent) from halogen-based (monovalent) perovskites in terms of their bulk moduli due to differences in valence states. Based on this model, high-throughput screening was performed on over 10,000 cubic chalcogenide and halide perovskites, identifying approximately 170 lead-free candidates with bulk moduli in the range of 10-20 GPa, comparable to Pb-I perovskites. These results provide preliminary evidence supporting the applicability of the soft-lattice mechanism in lead-free systems and offer theoretical guidance and data support for the high-throughput discovery of stable, defect-tolerant, lead-free perovskite materials.The dataset for this paper is available in the (Scientific Data Bank) database https://www.scidb.cn/s/A3IBBn.