About the Team:
Citi’s Global Consumer Bank (GCB) is a global leader in banking and wealth management, the world’s largest credit card issuer and a partner of choice globally to the world’s most iconic brands and digital leaders. The Global Consumer Bank serves more than 110 million clients in the U.S., Mexico and Asia, spanning 19 markets.
Risk Modeling Utility (RMU) is a centralized division of Citibank NA responsible for developing credit risk data driven empirical models and risk analytics solutions for all consumer credit businesses of Citi. These solutions span across all the phases of consumer credit cycle and geographies. The team consists of highly skilled data scientists with good understanding of consumer credit domain and regulatory requirements binding a bank.
Ideal Candidate Skills:
- The VP, Model/Anlys/Valid Officer will be a part of the RMU team based in the US. The candidate will be a strategic professional who will liaise with business stakeholders in the credit risk domain to understand the business requirements, priorities, challenges and will be able to cater towards data driven empirical risk models and analytics solutions complaint with OCC and other regulatory requirements.
- Data skills: The candidate should have proficiency in understanding and manipulating complex data in big data environment. Having sound understanding of the data is vital in any data science project.
- Collaboration skills: The candidate will have to collaborate with multiple stakeholders such as product team, business risk team, model implementation support and technology teams, model risk management and other data scientists in the team. The candidate should have apt inter-personal and collaboration skills.
- Communication skills: The role requires the use of complex multivariate statistical techniques for risk solutions. The candidate should be able to translate the complexity of work into parsimonious language.
- Technical Skills: The candidate should have good understanding of various statistical tools such as multivariate regression, cluster analysis, segmentation techniques, machine learning modeling techniques. Knowledge of database management. The candidate should have knowledge in SQL and be proficient in either SAS or Python.
- Personal Skills:
- Self-motivated & accountable – demonstrated ability to follow through to execution
- Problem-solving – gains energy through solving challenges and problems; able to handle and attack ambiguity as needed
- Ph.D. with 2 years of experience OR Master’s degree with ~ 4 years of experience in data analytics.
- Degree in quantitative fields such as Statistics, Mathematics, Operations Research, Financial Engineering preferred.
- Proficiency in advance SAS programming and/or Python programming.
- Comfortable with open-source languages and exhibits agility in developing further especially in big data cloud computing platforms.
- Preference for candidates who have experience with data management tools (SQL and Non-SQL)- Hadoop, Hive, Spark/ PySpark.
- At least 2 years of experience in developing empirical models using statistical and machine learning techniques such as Logistic Regression, Gradient Boosting, Random Forest, Deep Learning.
- Experience and knowledge about consumer credit risk will be given preference but not required.
- Technical: The candidate will be responsible for developing end-to-end risk models across different phases of consumer credit cycle such as acquisitions, behavior, collections, payment projection, recovery.
- Collaboration: After developing the respective credit risk scorecards, the candidate will participate in the implementation of sophisticated credit risk models in live operating environments within the organization.
- Business: The candidate will assist the internal businesses in the ongoing management and validation of their scores and score-based strategies.
- Communication: The candidate will be responsible for the preparation of all documentation related to model development, and for ensuring that such documentation is in full corporate and regulatory compliance.
- Innovation: The candidate will also participate in process automation and in the introduction of cutting-edge techniques of modeling and segmentation through innovative use of data to improve process and operational efficiencies wherever possible, thereby enhancing ability to make increasingly rapid credit decisions in the context of rapid changes in market conditions.
Job Family Group:
Risk Analytics, Modeling, and Validation
Citi is an equal opportunity and affirmative action employer.