Sr Data Scientist

PayPal•Chicago, IL

3d•$142,210 - $221,500•Hybrid

About The Position

Bill Me Later, Inc., a wholly-owned subsidiary of PayPal, Inc., seeks Sr Data Scientist in Chicago, IL. This role involves analyzing large, complex datasets to extract actionable insights that inform the project roadmap using advanced proficiency in Python, SQL, and other data science/analytical tools. The successful candidate will translate complex analytical, statistical, and modeling results into actionable, concise insights tailored for a range of stakeholders, including technical and non-technical audiences, leveraging experience handling large, complex data sets and building end-to-end data pipelines. The position requires designing, developing, and implementing robust Machine Learning and/or AI models to support Net Credit Loss (NCL) forecasting, reserve setting, and ongoing model monitoring, ensuring compliance with internal standards and regulatory requirements like CECL/IFRS9. Responsibilities also include designing and analyzing experiments (A/B, holdouts, quasi-experimentation methods) to validate hypotheses and quantify impact on key outcomes with statistical rigor, enhancing and automating existing NCL forecasting processes for continuous improvements in accuracy, scalability, and efficiency, and maintaining clear documentation and version control of all modeling procedures and code. The role demands partnering with Finance, Strategy, Collections, Risk, and Business teams to ensure accurate forecasting, effective stress testing, and appropriate reserve setting. Additionally, it involves monitoring and validating model performance, managing model risk, and supporting regular compliance reviews and audits in line with relevant regulatory standards and best practices. Experience with cloud-based solutions and version control (e.g., Git) is essential. The role will link analytical findings to business context, influencing key business decisions, and designing forward-looking strategies for risk mitigation and profit optimization. Partial telecommuting is permitted from a commutable distance.

Requirements

Master’s degree, or foreign equivalent, in Computer Science, Data Science, Statistics, Engineering, or a closely related field plus five years of experience in the job offered or a related occupation.
OR Bachelor’s degree, or foreign equivalent, in Computer Science, Data Science, Statistics, Engineering or a closely related field plus seven years of experience in the job offered or a related occupation.
Experience in developing credit risk models and collection strategies using statistical techniques (5 years)
Experience in Python programming for data analysis and machine learning (2 years)
Experience in SQL querying and relational database analysis, including complex joins, CTEs, and window functions (5 years)
Experience in Machine Learning algorithms including multivariate linear regressions, logistic regression, gradient boosting, decision trees, and XGBoost, and relevant techniques like data cleaning, exploratory data analysis, feature engineering, model evaluation, and hyperparameter tuning to optimize model performance (2 years)
Experience in profitability analysis, vintage monitoring and financial performance modeling for consumer credit products (5 years)
Experience in developing performance reporting and exceptions monitoring dashboards using data visualization tools including Tableau and Microsoft Excel (5 years)
Experience in A/B testing for enhancing collection strategies and portfolio performance (5 years)
Experience in Jira for model risk management, project management, and issue tracking (2 years)
Experience in cloud-based computing platforms like Snowflake, data pipeline management tools like Apache Airflow, and version control tools like Github (2 years)
Experience in end-to-end delivery of machine learning models and collection strategies including requirements, development, deployment, validation, and monitoring (2 years).

Nice To Haves

Partial telecommuting permitted from a commutable distance.

Responsibilities

Analyze large, complex datasets to extract actionable insights that inform the project roadmap using advanced proficiency in Python, SQL, and other data science/analytical tools.
Translate complex analytical, statistical, and modeling results into actionable, concise insights tailored for a range of stakeholders, including technical and non-technical audiences.
Design, develop, and implement robust Machine Learning and/or AI models to support Net Credit Loss (NCL) forecasting, reserve setting, and ongoing model monitoring.
Ensure models comply with internal standards and regulatory requirements, including CECL/IFRS9 where applicable.
Design and analyze experiments (A/B, holdouts, quasi-experimentation methods) to validate hypotheses and quantify impact on key outcomes with statistical rigor.
Enhance and automate existing NCL forecasting processes, driving continuous improvements in accuracy, scalability, and efficiency.
Maintain clear documentation and version control of all modeling procedures and code.
Partner with Finance, Strategy, Collections, Risk, and Business teams to ensure accurate forecasting, effective stress testing, and appropriate reserve setting.
Monitor and validate model performance, manage model risk, and support regular compliance reviews and audits in line with relevant regulatory standards and best practices.
Link analytical findings to business context, influencing key business decisions, and designing forward-looking strategies for risk mitigation and profit optimization.