Abstarct: Malaria is one of the most significant infectious and parasitic diseases worldwide and remains a serious public health threat, particularly in tropical and subtropical regions. The increasing drug resistance of Plasmodium falciparum has reduced the effectiveness of many antimalarial agents, highlighting the urgent need for the development of new compounds with potent biological activity. In this study, a hybrid computational frxamework baxsed on quantitative structure–activity relationship (QSAR) modeling was developed to predict the antimalarial activity of cyclopropylcarboxamide derivatives. To address the high dimensionality of the data and to identify relevant molecular descxriptors, the smoothly clipped absolute deviation (SCAD) penalized variable selection method was employed. The selected descxriptors were subsequently used as inputs for an artificial neural network (ANN) to model the nonlinear relationships between molecular structure and biological activity. The performance of the SCAD–ANN hybrid model was evaluated using various statistical parameters, and the results demonstrated satisfactory predictive accuracy and acceptable model stability. In addition, molecular docking studies were performed to investigate the binding interactions between the proposed compounds and the biological target. The docking results confirmed the formation of stable ligand–protein complexes and appropriate binding of the designed compounds within the active site of the target protein. Overall, the findings indicate that the integration of QSAR modeling, SCAD variable selection, ANN, and molecular docking provides an effective strategy for the rational design and evaluation of novel antimalarial compounds.