Principal Associate Data Scientist, Customer Protection Debit Transaction Fraud Data Science

Capital One Financial

Confirmed live yesterday Trusted

Quick summary

Work type: On-site
Location: McLean, VA
Salary: $161,800–$184,600 / yr
Posted: 31 days ago
Freshness: Confirmed live yesterday
Nearby: 99+ roles within 25 mi

Market check

Salary context

Competitive pay

How this pay compares to similar roles

Similar $180k

This role $173k

$133k most similar roles pay here $232k

This role pays less than 57% of similar roles. Most pay $146,150–$214,525 — the shaded band above. At the midpoint, this role pays about $173k versus about $180k for comparable roles.

Based on 240 similar postings.

Employer

About Capital One Financial

Capital One Financial is a bank holding company specializing in credit cards, auto loans, banking, and savings products, known for its data-driven approach to consumer and commercial finance. Industry: Financial Services & Banking

Capital One Financial currently has 998 open roles on FindRole.

Listed pay typically runs $197,300–$225,100 across 992 roles with salary data.

Most-posted roles

View all roles at Capital One Financial

At a glance

TL;DR · Principal Associate Data Scientist, Customer Protection Debit Transaction Fraud Data Science

Role Posting Log in to save

Principal Associate, Data Scientist - Customer Protection Debit Transaction Fraud Data Science joins the Bank Customer Protection Debit & Claims Data Science team to build machine learning models that protect customers from fraudulent activities and scams. The role involves developing purpose-built models for real-time debit authorization fraud detection by analyzing historical transaction activity, account usage, and merchant patterns. You will manage the full modeling lifecycle, including design, training, evaluation, validation, and implementation of techniques like gradient boosting, representation learning, graph learning, and sequence learning. To succeed, you must utilize a technical stack including Python, Conda, AWS, H2O, Spark, and SQL to process large volumes of numeric and textual data. The work focuses on identifying fraud signals in real-time systems to prevent negative impacts on customers by addressing emerging attack patterns across the debit authorization landscape.

What does a Data Scientist earn in Virginia?

Median $145200 from 75 postings across 5 companies.

See salary data

Skills

Python SQL AWS Spark H2O XGBoost LightGBM Kubernetes Kubeflow Pipelines Snowflake Snowpark Polars Conda Machine Learning Deep Learning Gradient Boosting Pytest MyPy

What you'll do

Build machine learning models for real-time debit authorization fraud detection using gradient boosting and frontier-AI approaches.
Develop and implement model lifecycles including design, training, evaluation, validation, and production deployment.
Analyze large volumes of numeric and textual data to identify fraudulent patterns and emerging attack signals.
Utilize a technical stack including Python, SQL, Spark, H2O, and AWS to extract insights from complex datasets.
Create automated modeling pipelines and reproducible workflows using MLOps tools like Kubeflow Pipelines.
Translate complex technical findings into tangible business goals for cross-functional stakeholders.
Perform model backtesting and performance measurement focusing on precision, recall, and capture rates.

What we're looking for

A Bachelor's degree in a quantitative field plus 5 years of experience performing data analytics.
A Master's degree in a quantitative field or an MBA with a quantitative concentration plus 3 years of experience performing data analytics.
A PhD in a quantitative field.
A Master’s Degree in a STEM field plus 3 years of experience in data analytics (preferred).
A PhD in a STEM field (preferred).
At least 3 years' experience with machine learning for predictive tasks, especially classification on large, highly imbalanced datasets (preferred).
At least 3 years' experience in Python and SQL (preferred).
Experience building gradient boosting models, automated modeling pipelines, or coordinating cross-functional projects (preferred).

Save