VP Fraud Risk Senior Manager (Data Scientist) - C13

Key Skills

Apache Hadoop, C Programming, C++, Data science techniques, Java Programming, Machine learning techniques, MapReduce, Python Programming, PyTorch, R Programming, Scala Programming, SQL, TensorFlow

Job Description

Citi’s Global Consumer Bank (GCB), a global leader in credit cards, wealth management and commercial banking, serves as a trusted partner to more than 110 million customers in 19 countries worldwide, providing financial services that enable growth and economic progress. The Global Consumer Bank operates four business lines — Branded Cards, Retail Services, Retail Banking and Commercial Banking — in three priority markets: Asia, Mexico and the U.S. Over the past few years, our business has transformed to become a simpler, leaner, focused franchise.

Citi is on a journey to become a world-class digital bank has tangibly accelerated with a mobile-first strategic focus and deployment of a new, agile operating model fostered massive improvements in the design and delivery of digital features and in the customer experience. As a result the franchise has seen significant growth in the number of digital users, mobile downloads and digital engagement.

About the GCB Fraud Prevention Organization

The financial crimes environment continues to be challenging, with cybercrime worldwide remaining highly lucrative and criminals becoming more organized and sophisticated, making it harder to distinguish between real and fraudulent customers. To combat the agile threat, the Global Consumer Bank (GCB) Fraud Prevention organization operates leveraging an intelligence-led, threat driven model that targets fraud along the entire fraud lifecycle, enabling the integration of analysis, dissemination of information and coordination of action with speed and agility across businesses and regions.

Fraud Risk Senior Manager (Data Scientist)

As part of the Fraud Analytics, Modeling & Intelligence organization, this role manages and executes the fraud analytics and strategies supporting Citi’s North American and global credit card and retail bank businesses. The role will utilize cutting-edge machine learning tools and data mining environment to identify fraud trends, designing and implementing strategies/models to prevent and mitigate fraud attacks across the fraud lifecycle, including application and synthetic ID fraud, account takeover and sophisticated new attack schemes.

This role partners closely with Fraud Policy, Operations and various partners to keep apprised of business and technology direction in order to determine potential and existing fraud impacts.

This role also may also have direct or indirect management responsibility of team members.

Responsibilities:

• Leverage analytics to identify enhancement opportunities and more granular insights that can be acted upon, while ensuring adherence to Fraud Policy.
• Build predictive models and machine-learning and AI algorithms with large amounts of structured and unstructured data.
• Ownership and management of fraud models, Risk appetite execution and defect analysis.
• Build effective relationships within and outside the Fraud organization to help ensure successful and timely execution of key portfolio priorities.
• Leverage knowledge of information acquired to identify potential process gaps and opportunities for improving effectiveness of controls and governance processes.
• Generate and manage regular and ad-hoc reporting to enable effective monitoring and identification of emerging trends.
• Continually assess manual and automated processes to identify potential process gaps and opportunities.
• Prioritize and provide a clear line of sight to the most critical work to partners and team members.
• Mentor and coach junior team members.

Qualifications:

• Bachelor’s Degree required in statistics, mathematics, physics, economics, or other analytical or quantitative discipline. Master's Degree or PhD preferred.
• 5+ years in relevant field.
• Experience working with:
• Big Data environment with hands on coding experience within various traditional (SAS, SQL, etc.) and/or open source (i.e. Python, Impala, Hive, etc.) tools.
• Traditional and advanced machine learning techniques and algorithms, such as Logistic Regression, Gradient Boosting, Random Forests, etc.
• Data visualization tools, such as Tableau
• Excellent quantitative and analytic skills; ability to derive patterns, trends and insights, and perform risk/reward trade-off analysis.
• Good written and verbal communication skills, with ability to connect analytics to business impacts; comfortable presenting to peers and management.
• Ability to build effective presentations to communicate analytical findings to a wide array of audiences.
• Effective cross-functional project, resource, and stakeholder engagement and management, with ability to effectively drive collaboration across teams.
• Ability to make decisions independently with minimal guidance from management.