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

Capital One Financial

Confirmed live today Low trust

Quick summary

Work type: On-site
Location: McLean, VA
Salary: $161,800–$184,600 / yr
Employment: Full-time
Posted: 77 days ago
Freshness: Confirmed live today
Nearby: 99+ roles within 25 mi

Market check

Salary context

Competitive pay

How this pay compares to similar roles

Similar $183k

This role $173k

$135k $235k

below market most similar roles pay here above market

This role pays less than 55% of similar roles. Most pay $149,625–$215,700 — the blue band above. At the midpoint, this role pays about $173k versus about $183k 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 2107 open roles on FindRole.

Listed pay typically runs $197,300–$225,100 across 1107 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. You will partner with cross-functional teams to develop models that identify fraud signals in real-time during debit authorizations by analyzing historical transaction activity, account usage, and merchant patterns. The role involves building models through all phases of development, including design, training, evaluation, and implementation. You will utilize a technology stack including Python, Conda, AWS, H2O, Spark, and SQL. Key methodologies include representation learning, gradient boosting machines, graph learning, and sequence learning. You will solve the business problem of stopping debit fraud instantly while managing large-scale numeric and textual data to ensure customer safety.

What does a Data Scientist earn in Virginia?

Median $162000 from 89 postings across 9 companies.

See salary data

Skills

Python SQL AWS Spark H2O XGBoost LightGBM Kubernetes Kubeflow Pipelines Snowflake Snowpark Polars Conda Pytest Mypy Deep Learning Gradient Boosting Sequence Learning Time Series Sentiment Analysis Clustering Classification Representation Learning

What you'll do

Build machine learning models through all phases of development, including design, training, evaluation, validation, and implementation.
Develop real-time decision systems to detect and stop debit authorization fraud as transactions occur.
Analyze historical transaction activity, account usage, and merchant patterns to identify signals of fraudulent activity.
Utilize a technology stack including Python, SQL, Spark, and AWS to extract insights from large volumes of numeric and textual data.
Implement advanced methodologies such as gradient boosting, representation learning, graph learning, and sequence learning.
Orchestrate automated modeling pipelines for reproducible training, evaluation, and deployment workflows.
Translate complex technical work into tangible business goals for cross-functional stakeholders.
Perform model backtesting and performance measurement using metrics like precision, recall, and ROC curves.

What we're looking for

Bachelor's Degree in a quantitative field plus 5 years of experience performing data analytics.
Master's Degree in a quantitative field or an MBA with a quantitative concentration plus 3 years of experience performing data analytics.
PhD in a quantitative field.
Master’s Degree in a STEM field plus 3 years of experience in data analytics (preferred).
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 and tuning gradient boosting models and deploying them into real-time or production decision systems (preferred).

Save