Neglected tropical diseases, including malaria, burden global health, but the research into treatments and drug targets remains limited. While technology has revolutionized drug discovery for wealthier nations, neglected tropical diseases have not seen the same progress. Machine learning offers an efficient and labor-saving alternative for identifying potential drug targets compared to conventional methods. This research work introduces a novel approach to identify potential drug targets for malaria, utilizing machine learning algorithms. The methodology involves the construction of a machine learning model, which is evaluated on a dataset comprising malaria human drug targets and nontargets. The dataset is curated by building a protein-protein interaction network, and the network centrality features have been extracted. Additionally, the protein sequence properties of these proteins are incorporated for analysis. Multiple classification methods were implemented, with Gradient Boosting and Random Forest algorithms demonstrating the most promising outcomes. These classifiers are employed to identify novel human targets. Subsequently, approved drugs like Ketoconazole, Gentian Violet, and Doxorubicin Hydrochloride associated with these targets are identified, which can be potential contenders for recovery from malaria.