Job Summary
What you need to know about the role
We are looking for Manager Data Science with experience of Managing large portfolios to develop PayPal s Risk strategy within the SMB Fraud Risk solutions team. Manager Data Science will be the end-to-end owner of the consumer risk for SMB products and is responsible for end-to-end management of loss and decline rates. Day-to-day duties include leading a team of data scientists to deliver impactful, data-driven solutions across the business. This role combines technical expertise with strategic leadership to guide end-to-end project execution, from defining business problems to deploying models and delivering insights. The manager also aligns cross-functional stakeholders and ensures the Risk strategy function contributes meaningfully to business growth and innovation. Meet our team PayPals Global Fraud Protection team is responsible for partnering with global business units to manage a variety of risk of various types, including identity fraud, account takeover, stolen financial fraud, and credit issues. This is an exciting department that plays an important role in contributing PayPals bottom line financial savings, ensuring safe and secure global business growth, and delivering the best customer experience. This open opportunity is within the SMB Fraud Risk team. This portfolio is comprised of PayPal s leading-edge SMB payments solutions, such as Bill Pay, Invoicing, Zettle, Donations etc. as well as customized experiences developed for the company s highest-priority strategic Markets and Partnerships.
Job Description
You will be the Manager Data Science in the Fraud Risk team , where you will work on leading new projects to build and improve the Risk strategies to prevent fraud using the Risk tooled and custom data & AL/ML models. In this position, you will be partnering with the corresponding Business Units to align with and influence their strategic priorities, educate business partners about Risk management principles, and collaboratively optimize the Risk treatments and experiences for these unique products and partners.
In your day-to-day role you will -
What do you need to bring-
-
Technical Proficiency Exploratory Data Analysis and expertise in preparing a clean and structured data for model development. Experience in applying AI/ML techniques for business decisioning including supervised and unsupervised learning (e.g., regression, classification, clustering, decision trees, anomaly detection, etc.). Knowledge of model evaluation techniques such as Precision, Recall, ROC-AUC Curve, etc. along with basic statistical concepts.