The rapid growth of Android devices has led to a significant increase in malware targeting mobile platforms, posing serious security threats to users and organizations. Traditional malware detection methods often fail to identify new and evolving threats due to their reliance on signature-based techniques. This project proposes an intelligent Android malware detection system that integrates machine learning with Genetic Algorithm (GA)-based feature optimization. The system extracts static and dynamic features from Android applications and applies GA to select the most relevant features, reducing dimensionality and improving model performance. Machine learning algorithms such as Random Forest, Support Vector Machine, and Logistic Regression are then used for classification. The proposed approach enhances detection accuracy, reduces false positives, and improves computational efficiency. Experimental results demonstrate that GA-based feature optimization significantly boosts the effectiveness of malware detection models, making the system robust and scalable for real-world applications.