Results that are similar to your search
Similar results
Thrilled to share that I have officially completed the training program at Manara!
Throughout this journey, I’ve deeply enhanced my technical skills in data and machine learning, working through rigorous projects and sharpening my expertise in building scalable, real-world solutions.
A huge thank you to the entire Manara team and mentors for the incredible guidance and support. This is a solid milestone, and I’m super excited for the next chapter—gearing up for the AWS Certified Machine Learning Engineer exam and diving deeper into MLOps!
#Manara #MachineLearning #DataEngineering #MLOps #AWS #ContinuousLearning
4
3
781
This project takes a fraud-detection model built in a notebook and turns it into a small, runnable system you can demo and deploy locally. In my workflow, I start with the notebook, save a single artifact, then wrap it with an API, a UI, and basic monitoring.
1 (https://1). Train and evaluate a model on creditcard.csv
2. Save a deployable artifact (.pkl)
3. Serve predictions through a FastAPI backend
4. Provide a Streamlit UI for manual testing and batch scoring
5. Log predictions and feedback labels for monitoring
6. Run basic drift checks and export feature importance for sanity checks
What Problem This Solves
Fraud detection is a highly imbalanced classification problem, so "accuracy" is usually misleading. What you typically want is:
1 (https://1). a risk score (fraud probability) per transaction
2. a decision policy (threshold) you can tune to match operational goals (precision/recall tradeoff)
3. serving layer so the model works outside Jupyter
4. a monitoring loop so you can detect drift and decide when to retrain
1
149
