This study comprehensively evaluates malware detection using machine learning techniques, focusing on the Mal-API-2019 dataset. The research aims to enhance cybersecurity by identifying and mitigating threats more effectively. Various classification models, including ensemble and non-ensemble methods such as Random Forest, XGBoost, K Nearest Neighbor (KNN), and Neural Networks, are explored. The importance of data preprocessing techniques, such as TF-IDF representation and Principal Component Analysis (PCA), is emphasized to improve model performance. Results indicate that ensemble methods, particularly Random Forest and XGBoost, exhibit superior accuracy, precision, and recall compared to other models. The study also discusses limitations and future directions, highlighting the need for continuous adaptation to address evolving malware threats. This research contributes to ongoing discussions in cybersecurity and provides practical insights for developing more robust malware detection systems.This study comprehensively evaluates malware detection using machine learning techniques, focusing on the Mal-API-2019 dataset. The research aims to enhance cybersecurity by identifying and mitigating threats more effectively. Various classification models, including ensemble and non-ensemble methods such as Random Forest, XGBoost, K Nearest Neighbor (KNN), and Neural Networks, are explored. The importance of data preprocessing techniques, such as TF-IDF representation and Principal Component Analysis (PCA), is emphasized to improve model performance. Results indicate that ensemble methods, particularly Random Forest and XGBoost, exhibit superior accuracy, precision, and recall compared to other models. The study also discusses limitations and future directions, highlighting the need for continuous adaptation to address evolving malware threats. This research contributes to ongoing discussions in cybersecurity and provides practical insights for developing more robust malware detection systems.