Malware is malicious software employed to disrupt, disable, or invade operating systems and user hardware without consent. Android, the dominant smartphone operating system, faces enormous malware threats as smartphone usage grows exponentially. Traditionally employed pattern-based malware detection approaches have limitations, which has created interest in artificial intelligence (AI)-based approaches. In this paper, we worked with an Android malware dataset of 355,630 network flow records to build a strong AI-based detection model. The dataset consists of four classes: Android Adware, Scareware, SMS Malware, and Benign, with severe class imbalance. This research was conducted through exploratory data analysis (EDA) and strict feature selection techniques to identify significant features. We applied the synthetic minority over-sampling technique (SMOTE) to address the class imbalance in an optimized ensemble machine-learning pipeline comprising Random Forest, XGBoost, LightGBM, ExtraTrees, and CatBoost classifiers. We also contrasted the models based on fivefold Stratified cross-validation, hyperparameter tuning, and feature conversion. Among the classifiers, the hyperparameter-tuned Random Forest model achieved the best performance of an F2-score of 92%. Furthermore, we deployed the best-performing model using FastAPI and Streamlit frameworks, providing an interactive web-based detection platform that enhances practical usability. This research offers valuable insights and robust methods for protecting Android users against evolving malware threats.