PaySafe India — Real-Time UPI Fraud Detection with Open-Source ML (No Cloud Required)

Описание и применение

Система PaySafe India обеспечивает реальное‑временное обнаружение мошеннических транзакций UPI с использованием полностью локального, открытого ML‑стека, предоставляя точные оценки риска и объяснения без выхода данных в облако.

Задача

Detect fraudulent UPI transactions in real time without relying on cloud services or external APIs, ensuring data stays local and costs are minimal.

Результат

Random Forest model achieved 0.983 precision, 0.879 recall, 0.928 F1, and 0.969 ROC‑AUC on a held‑out test set of 5,279 transactions, outperforming other classifiers and a dummy baseline.

Рабочий процесс

• Select and audit dataset for leakage
• Clean and engineer behavioral features
• Apply K‑Means clustering for anomaly pre‑check
• Train four supervised classifiers with cross‑validation
• Choose best model based on CV F1
• Serialize model with joblib
• Deploy Flask app with REST API and counterfactual explainability

Доказательства

Random Forest (deployed ✅) 0.983 precision, 0.879 recall, 0.928 F1, 0.969 ROC‑AUC

Источник

The Flask web app runs locally at http://127.0.0.1:5000 after a one‑time training run.

Источник

No LLM. No cloud ML service. No API keys. Just classical ML running at full speed on a laptop.

Источник