The primary purpose of this work is to extract features from decompiled Android app packages (APKs) so that Machine Learning (ML) models can appropriately detect malware. The purpose of this research is to understand more about how Android apps work and what they do by examining APK files and extracting key static elements like as permissions, API calls, intentions, opcodes, and manifest data. These features are used to train several machine learning approaches, including Decision Trees, Random Forests, Support Vector Machines, and Neural Networks, to distinguish between good and bad apps. The proposed strategy improves malware detection by identifying hidden harmful patterns and depending less on standard signature-based methods. Researchers discovered that employing feature-based machine learning to categorize emerging Android malware threats improves their detection, scalability, and accuracy. This means that both mobile apps and laptops can be protected against cyber threats.