Senior Data Scientist

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

Senior Data Scientist at PayPal in Chicago, IL, focused on developing and implementing advanced data science models for identity, onboarding, authentication, abuse, and scam detection within the financial technology domain. The role involves leveraging Python, SQL, and BigQuery for risk decisioning, collaborating with cross-functional teams, and applying statistics, machine learning, and AI to fraud detection. Key responsibilities include maintaining loss targets, optimizing risk experience, ensuring data quality, and exploring advanced technologies like AI, ML, and LLMs to evolve risk strategies. The position requires a Master's degree or equivalent with 2 years of experience in applying ML algorithms for fraud detection, developing regression-based default models, conducting large-scale data analysis with SQL/Python/Spark, building data pipelines, deploying models to production, and analyzing transactional data for fraud indicators.

What you'd actually do

  1. Lead the development and implementation of advanced data science models.
  2. Design and implement core decision models for identity, onboarding, authentication, abuse, scam, product-specific models by leveraging Python, SQL languages, and BigQuery tool to design and implement risk decision.
  3. Collaborate with stakeholders to understand requirements.
  4. Work closely with cross-functional teams, including engineers, operations, and product teams, to integrate fraud prediction models and strategies into various systems and processes.
  5. Drive best practices in data science.

Skills

Required

  • Applying machine learning algorithms on financial data for fraud detection, abuse detection, identity risk or risk assessment, using supervised learning and unsupervised learning (logistic regression, gradient boosting, random forest, clustering) (2 years)
  • Developing, training, calibrating and validating regression-based default models for fraud or risk prediction (2 years)
  • Conducting analysis using SQL/SAS/Python in database/server for large-scale data analysis (2 years)
  • Performing data manipulation and processing using distributed computing frameworks such as PySpark/Spark for feature engineering, model training, or analytics (2 years)
  • Building scalable data pipelines for analytics or model training using Python, SQL, or cloud-based tools (2 years)
  • Developing, testing, and operating model training or scoring pipelines in Python on cloud environments using distributed computing clusters (2 years)
  • Building and deploying automated dashboards and benchmarks for fraud or risk related metrics monitoring using Python, Tableau, and Snowflake (2 years)
  • Deploying analytical or machine learning models into production and maintain key documentation in production environment on cloud (2 years)
  • Analyzing transactional or behavior data to identify anomalies, patterns or potential fraud indicators using statistical or machine learning methods (2 years)
  • Working with cross-functional teams including risk, engineering, and product partner, to translate fraud business requirements into analy

What the JD emphasized

  • fraud detection
  • risk modeling
  • machine learning
  • AI applications
  • data quality and integrity
  • data engineering team
  • risk strategies
  • risk modelling

Other signals

  • fraud detection
  • risk modeling
  • machine learning
  • AI applications