Logo Lanfrica
  • Accueil
  • Atlas
  • Analyses
  • Documentation
  • Sign in

© 2026 Lanfrica. Tous droits réservés. Tous les droits d'auteur des ressources affichées sur le site Web Lanfrica appartiennent aux détenteurs de droits d'auteur d'origine, sauf indication contraire explicite.

AshleyNyaboke/mobile-money-fraud-detection

Domaine:

digital infrastructuresocioeconomic

Type de record:

model
Créateur:
Ash
Hôte:
AI fraud detection system for Kenya's mobile money ecosystem — 98% accuracy, built with Isolation Forest # 🔍 Mobile Money Fraud Detection System > AI-powered real time fraud detection for Kenya's mobile > money ecosystem — built with Isolation Forest. **Live Dashboard:** Click Here --- ## 🎯 Project Overview Kenya processes over 61 million mobile money transactions daily. This AI system detects suspicious M-Pesa style transactions in real time using Isolation Forest — the gold standard algorithm for fraud detection in fintech. **Model Performance:** - Accuracy: 98% - AUC Score: 0.9925 - KSh Saved: 12,528,427 ## 🦹 6 Fraud Types Detected - 🌙 Night Owl Fraud - 💸 Large Amount Anomaly - ⚡ Velocity Fraud - 🔄 Round Trip Fraud - 👥 Mule Account Fraud - 📱 SIM Swap Fraud ## 🏦 Built For Safaricom | Airtel Money | Absa Bank Kenya | Equity Bank | KCB Bank Kenya ## 👩🏾‍💻 Built By **Ashley Nyaboke Kibwogo** Junior Data Scientist | AI & ML for Kenya Fintech 🇰🇪 🔗 LinkedIn 💻 GitHub

Visit

github.com