BBBahati Brenda Kizitoingodfident-data.hashnode.dev·Aug 17 · 8 min readMy Model Worked… Until I Actually Looked at the DataI thought I had a working model. The numbers looked clean. Accuracy sat comfortably high. The pipeline ran without errors. I even started thinking about how I would present the results. Then I actuall00
BBBahati Brenda Kizitoingodfident-data.hashnode.dev·Aug 16 · 6 min readI Tried Predicting House Prices… Then scikit-learn Gave Me a History LessonI just wanted to predict house prices. I opened a notebook, typed the familiar import, and wrote the line I had seen in dozens of tutorials: from sklearn.datasets import load_boston boston = load_bost00
BBBahati Brenda Kizitoingodfident-data.hashnode.dev·Aug 15 · 8 min read99% Accuracy Is Not Always Good: What Fraud Detection Taught Me About MLI built a fraud detection model that hit 99% accuracy. I was proud of it for about twelve minutes. Then I looked closer and realized the model was basically doing nothing useful. This is the story of 00
BBBahati Brenda Kizitoingodfident-data.hashnode.dev·Feb 18 · 5 min readTraining a Model to Catch Fraud (And It Humbled Me) - Lessons from Building a Real Fraud Detection SystemIf you’ve ever built a machine learning project that worked beautifully on your laptop but humbled you in production… welcome to my life 😭 Today I’m sharing my journey building CreditWise AI — my credit card fraud detection project — and everything ...10
BBBahati Brenda Kizitoingodfident-data.hashnode.dev·Feb 18 · 6 min readDriftGuard AI: My Journey Into Smart Data Monitoring and AI Automation 🚀Hey friends! 🌸 If you’ve been following my tech adventures, you know I love building projects that are faith-led, data-driven, and future-focused. Today, I’m sharing one of my favorite journeys: building DriftGuard AI, a system to monitor AI models ...00
