Google Maps–Inspired AI Traffic Route Guidance | Deep Learning + Heuristic Search | Real-World SCATS Data (Boroondara 2006)

Built a machine learning pipeline to detect fraudulent credit card transactions using real-world data (1M+ rows). Explored fraud patterns, validated key hypotheses, and optimized models like KNN, Random Forest, and SVM with 98%+ recall. Strong focus on data insights & impact.

Statistical analysis of NYC TAP funding across colleges using Python, EDA, hypothesis testing, and real 260K-row dataset.