Sr Data Scientist

PayPal•San Jose, CA

2d•$174,783 - $243,500•Hybrid

About The Position

PayPal, Inc. seeks Sr Data Scientist in San Jose, CA. This role involves applying advanced analytical and technical skills to research multi-dimensional data sets, implement continuous monitoring protocols, and develop complex algorithmic logics that identify and prevent fraudulent activity on our platforms in real-time. The position requires designing, constructing, and validating statistical models using advanced analytical tools to transform raw transactional data into actionable insights for fraud detection. The Sr Data Scientist will leverage advanced data analytics and statistical methodologies to identify emerging fraud patterns and trends across payment ecosystems, such as NSF, SF, INR, and SNAD. A key responsibility is developing, implementing, and maintaining sophisticated real-time risk assessment solutions that carefully balance organizational loss appetite, user experience metrics, and product financial performance KPIs. The role also includes conducting rigorous A/B testing to evaluate the effectiveness of fraud detection models and risk controls, measuring the statistical significance of results and implementing enhancements based on findings. Creating and maintaining comprehensive data visualization dashboards using tools like Tableau or Power BI to track key risk metrics, providing stakeholders with actionable intelligence on fraud trends and control effectiveness, is also part of the job. Furthermore, the Sr Data Scientist will perform detailed root cause analysis of fraud cases and security breaches, identifying systemic vulnerabilities and developing technical solutions to address them. This role requires cross-functional partnership with Product Management and Business Unit organizations to support new product launches, conducting thorough risk assessments and creating comprehensive risk mitigation requirements. Close collaboration with risk product engineering teams to translate complex risk requirements into technical specifications, ensuring accurate implementation and seamless delivery of fraud prevention capabilities, is essential. The Sr Data Scientist will develop and document risk frameworks and methodologies that allow for consistent evaluation and mitigation strategies across diverse product offerings. Presenting complex analytical findings to senior leadership and non-technical stakeholders, translating technical concepts into business-relevant insights, is a crucial aspect of this position. Maintaining current knowledge of evolving fraud methodologies, financial industry regulations, and technological advancements in the risk management field, and applying this knowledge to continuously improve fraud prevention systems, is expected. The role also involves mentoring junior analysts in advanced statistical techniques and fraud detection methodologies, supporting knowledge transfer across the risk organization. Partial telecommuting is permitted from within a commutable distance.

Requirements

Master’s degree, or foreign equivalent, in Data Science, Mathematics, or a closely related field, plus three years of experience in the job offered or a related occupation.
Fraud Detection and Root Cause Analysis: Experience performing root cause analysis on fraud cases within financial transaction systems and implementing data-driven mitigation strategies in production. (3 years);
Python for Fraud Modeling: Experience using Python (NumPy, Pandas) for data processing and feature engineering, and applying Scikit-learn for fraud model development on large-scale financial transaction datasets. (3 years);
Risk Metrics Dashboard Development: Experience building Tableau dashboards to monitor fraud risk KPIs for decision-making. (3 years);
Cloud-Based and Distributed Data Analytics: Experience writing complex SQL queries on cloud-based data platforms and working with distributed data systems to analyze large-scale financial transaction data, including building and maintaining data pipelines and workflows in data warehouse environments. (3 years);
Statistical Modeling and Experimentation: Experience applying statistical models and conducting A/B testing on customer-facing risk strategies and supporting new product initiatives, including hypothesis testing and impact measurement. (3 years);
Payment Ecosystem Knowledge: Experience utilizing knowledge of payment flows and the MANIC model (Merchant, Acquirer, Network, Issuer, Cardholder) in fraud detection contexts. (3 years);
Machine Learning for Fraud Detection: Experience building and deploying machine learning models using Python frameworks (H2O or similar platforms) for real-time fraud detection on large-scale financial transaction datasets. (3 years);
Fraud Pattern Analysis and Risk Strategy: Experience analyzing fraud patterns in financial transaction data and developing risk strategies to support new product initiatives while balancing fraud loss, customer experience, and business KPIs. (3 years);
Version Control and Automation: Experience using GitHub for version control and implementing automated workflows to support scalable fraud analytics and modeling. (3 years).

Responsibilities

Apply advanced analytical and technical skills to research multi-dimensional data sets, implement continuous monitoring protocols, and develop complex algorithmic logics that identify and prevent fraudulent activity on our platforms in real-time.
Design, construct, and validate statistical models using advanced analytical tools to transform raw transactional data into actionable insights for fraud detection.
Leverage advanced data analytics and statistical methodologies to identify emerging fraud patterns and trends across payment ecosystems, such as NSF, SF, INR, and SNAD.
Develop, implement, and maintain sophisticated real-time risk assessment solutions that carefully balance organizational loss appetite, user experience metrics, and product financial performance KPIs.
Conduct rigorous A/B testing to evaluate the effectiveness of fraud detection models and risk controls, measuring the statistical significance of results and implementing enhancements based on findings.
Create and maintain comprehensive data visualization dashboards using tools like Tableau or Power BI that track key risk metrics, providing stakeholders with actionable intelligence on fraud trends and control effectiveness.
Perform detailed root cause analysis of fraud cases and security breaches, identifying systemic vulnerabilities and developing technical solutions to address them.
Partner cross-functionally with Product Management and Business Unit organizations to support new product launches, conducting thorough risk assessments and creating comprehensive risk mitigation requirements.
Work closely with risk product engineering teams to translate complex risk requirements into technical specifications, ensuring accurate implementation and seamless delivery of fraud prevention capabilities.
Develop and document risk frameworks and methodologies that allow for consistent evaluation and mitigation strategies across diverse product offerings.
Present complex analytical findings to senior leadership and non-technical stakeholders, translating technical concepts into business-relevant insights.
Maintain current knowledge of evolving fraud methodologies, financial industry regulations, and technological advancements in the risk management field, applying this knowledge to continuously improve fraud prevention systems.
Mentor junior analysts in advanced statistical techniques and fraud detection methodologies, supporting knowledge transfer across the risk organization.