Sr Data Scientist

PayPal PayPal · Fintech · Chicago, IL +1 · Data Science

Senior Data Scientist at PayPal in Chicago, IL, focused on developing and implementing credit risk strategies for PayPal and Venmo credit card programs. The role involves using mathematical, statistical, and data mining methods, including machine learning for model development and deployment, to balance risk and reward, user experience, and financial performance. Responsibilities include automating tracking, testing new data sources, providing insights through monitoring and reporting, and performing operational monitoring. Requires expertise in credit risk management, predictive analytics, experimental design, machine learning, P&L analytics, credit bureau analytics, Python (pandas, numpy, sklearn), SQL (Big Query, Teradata), data visualization tools (Tableau, Amplitude), and database management (Hadoop, Hive, Stampy, Teradata, Big Query).

What you'd actually do

  1. Develop and implement credit risk strategies for various products, including PayPal and Venmo credit card programs.
  2. Ensure strategies are reviewed and approved within the approved governance committee structures.
  3. Develop and automate tracking functionality that monitors volume and strategy performance.
  4. Test new data sources to enhance credit risk decisions.
  5. Provide PayPal and Venmo Card program insights via monitoring and reporting leveraging internal/external data.

Skills

Required

  • Credit risk management / analytics in consumer lending space
  • Predictive analytics and segmentation in consumer lending credit risk area (classification models, regression models, and statistical analysis)
  • Experimental design (A/B testing) in consumer lending credit risk area
  • Machine learning (model development/deployment; optimization including parameter tuning, dimension reduction, feature selection, and model validation) in consumer lending credit risk area
  • Profit & Loss (P&L) analytics in the consumer lending area
  • Credit bureau analytics
  • Python (pandas, numpy, and sklearn packages)
  • SQL tools: Google Big Query and Teradata
  • Data visualization / Business Intelligence tools (Tableau, Amplitude, and Q-monitor)
  • Database management: Big data and cloud (Hadoop, Hive, Stampy, Teradata, and Google Big Query)
  • Forecasting techniques/algorithms and automation with Python

What the JD emphasized

  • Credit risk management / analytics in consumer lending space (4 years)
  • Predictive analytics and segmentation in consumer lending credit risk area (classification models, regression models, and statistical analysis) (4 years)
  • Machine learning (model development/deployment; optimization including parameter tuning, dimension reduction, feature selection, and model validation) in consumer lending credit risk area (4 years)
  • Credit bureau analytics (4 years)

Other signals

  • Develop and implement credit risk strategies
  • Employ mathematical, statistical and data mining methods
  • Machine learning (model development/deployment; optimization including parameter tuning, dimension reduction, feature selection, and model validation) in consumer lending credit risk area