Position Details
About this role
Principal Associate Data Scientist (SBB Fraud) role building machine learning models to protect Small Business Bank customers against fraud. You will develop and deploy fraud models through the full lifecycle and communicate results into business goals.
Key Responsibilities
- Build machine learning models through design, training, evaluation, validation, and implementation
- Leverage Python, Conda, AWS (Amazon Web Services), H2O, Spark for fraud insights
- Partner cross-functionally to deliver fraud-focused products
- Validate and backtest models using confusion matrix and ROC curve
- Translate modeling complexity into tangible business goals
Technical Overview
Use Python with AWS (Amazon Web Services), H2O, and Spark to build machine learning fraud models. Apply statistical and ML methods including clustering, classification, sentiment analysis, time series, and deep learning, with evaluation via confusion matrix and ROC curve and strong backtesting practices.
Ideal Candidate
The ideal candidate is a data scientist with strong hands-on experience building and validating machine learning fraud models for small business banking use cases. They can demonstrate proficiency with Python, AWS (Amazon Web Services), H2O, and Spark, and have measurable modeling expertise using metrics like confusion matrices and ROC curves.
Must-Have Skills
Nice-to-Have Skills
Tools & Platforms
Required Skills
Hard Skills
Soft Skills
Industry & Role
Keywords for Your Resume
Deal Breakers
Must have experience building validated and backtested machine learning models, Must demonstrate knowledge of confusion matrix and ROC curve, Must have hands-on experience with Python and AWS (Amazon Web Services)
Get matched to jobs like this
Luna finds roles that fit your skills and career goals — no endless scrolling required.
Create a Free Profile