Expert Data Scientist, Fraud Risk Detection

Experian•Madison, MS

1d•$137,102 - $246,784•Remote

About The Position

Experian is seeking a Data Scientist for its Fraud Analytics & Commercialization organization. The role focuses on building fraud-detection models and features that identify high-risk activity while minimizing friction for legitimate customers. The scientist will investigate emerging fraud patterns, develop features, and train and evaluate machine-learning models, working with senior data scientists and engineers from problem definition through feature engineering, experimentation, and deployment. The position calls for translating theoretical principles into production-ready solutions and contributing to research and engineering that support commercialized tools and systems. The role is remote and reports to the Sr. Manager of Fraud Analytics. The position is full-time and has a stated day shift. The posted annual salary range is $137,102–$246,784, with eligibility for variable pay and a comprehensive benefits package.

Requirements

At least 5 years of experience in data science, machine learning, statistical modeling, or a related quantitative field.
Bachelor's or advanced degree in computer science, statistics, engineering, data science, or another quantitative discipline.
Direct experience developing fraud-detection, identity-risk, credit-risk, financial-crime, or other adversarial risk models.
Demonstrated experience creating meaningful fraud features.
Proficiency in Python and PySpark, including writing modular and tested code for large datasets and distributed or cloud data systems.
Experience with common data science and machine-learning tools such as pandas, NumPy, scikit-learn, XGBoost, TensorFlow, or comparable technologies.
Knowledge of supervised learning, model evaluation, feature selection, statistical inference, experimentation, and model calibration.
Experience addressing fraud-modeling challenges, including class imbalance, delayed or incomplete labels, changing attack patterns, and model drift.
Experience moving models beyond experimentation into production, directly or in close partnership with engineering teams.

Responsibilities

Investigate large datasets through exploratory analysis and fraud-label development to identify emerging fraud patterns, attack methods, and behavioral signals.
Translate ambiguous fraud and risk problems into hypotheses, analytical plans, model requirements, and measurable success criteria.
Develop machine-learning models for fraud detection involving account opening, account takeover, and identity risk.
Evaluate models using measures such as ROC/AUC/KS/Gini, precision and recall, fraud capture rate, false-positive rate, customer friction, and fraud losses prevented.
Develop and validate predictive features using identity, transactional, consumer credit history, device, behavioral, temporal, velocity, network, and third-party data.
Write clean, efficient, well-tested Python and PySpark code and collaborate to bring models and features into batch, retro, or real-time decisioning environments.
Monitor feature quality, model performance, population changes, and fraud-pattern drift.
Design and present analyses of model behavior, tradeoffs, risks, and recommendations.
Follow standards for data privacy, model documentation, explainability, validation, and governance.