The process of screening and developing new drugs through experiments is very slow and requires a lot of manpower and material resources, and the use of computer-aided prediction of the molecular properties of drugs can greatly save time and cost of drug development. Therefore, in order to enable anti-breast cancer candidate drugs to have good biological activity and ADMET properties for inhibiting ERα, the random forest classifier was first used for the collected 1974 compounds to screen the top 20 molecular descriptors with the most significant effects on biological activity. Then a QSAR model was established using this and ${\rm pIC}_{50}$ value as characteristic data. The biological activity values of 50 new compounds were predicted via the PSO optimized BP neural network, with the model fit of 0.8337 and the root mean square error of 0.7315, which were more consistent with the actual values than the predicted results of the BP neural network. Subsequently, in order to improve the success rate of drug development, the ADMET classification prediction model was constructed using PSO to optimize the SVM based on the existing ADMET property data. The algorithm cross-validation CV accuracy rate reached 94.0767%, and the prediction accuracy rates of the five index models were all above 79%. The results show that the proposed model has better prediction performance than the benchmark model, and the adopted prediction strategy is effective, which can provide reference for the discovery and development of anti-breast cancer drugs.