Data Scientist I - Model Governance - Fraud Prevention and Detection

Bank of America•Charlotte, NC

7d•Onsite

About The Position

Bank of America’s Fraud Prevention and Detection team is seeking a model validation professional to help combat financial crime. The role analyzes and interprets large datasets to uncover potential revenue opportunities and develop risk-management strategies. It involves working with stakeholders to understand business problems, applying data-gathering and analysis techniques, and presenting recommendations based on findings. The position develops and validates models and other analytical solutions, creates technical documentation, and collaborates with developers, technology teams, model users, independent model risk management, legal, and compliance teams. The work includes planning model deployments, validating and monitoring model performance, identifying and mitigating risks, and ensuring models meet governance and approval requirements. The position also supports Bank policy and governance requirements for artificial intelligence models and researches advances in data science and AI. Bank of America describes its workplace approach as an in-office culture that supports collaboration, engagement, and career development, with role-specific flexibility based on responsibilities and business needs. The role is designated first shift and is listed at 40 hours per week.

Requirements

A quantitative undergraduate or graduate degree, or relevant certifications and experience.
At least 3 years of experience in model validation or development.
Experience with model governance, model documentation, model monitoring, and interactions with model risk management functions.
Strong analytical skills, including investigating performance trends, identifying root causes, and recommending solutions.
Proficiency with SQL and SAS.
Excellent technical writing skills.
Critical problem-solving abilities, including selecting data and deploying solutions.
Excellent communication and influencing skills.
Ability to thrive in a fast-paced, highly dynamic environment.
Intellectual curiosity and a strong desire to understand problems and develop creative solutions.

Nice To Haves

Advanced quantitative degree (Master’s or PhD).
Five or more years of experience working in model validation.
Financial services experience; familiarity with SR-26-2 guidance is highly desirable.
Working knowledge of Python.

Responsibilities

Perform business analytics, including data analysis, trend identification, and pattern recognition using techniques such as machine learning, text mining, and statistical analysis.
Apply agile practices to project management, solution development, deployment, and maintenance.
Create and maintain technical documentation covering business requirements and specifications for analytical solutions and their production implementation.
Manage multiple priorities and deliver quantitative models, data science products, analysis reports, and visualizations with quality and timeliness, working independently and collaboratively.
Present technical concepts and analytical results to diverse internal stakeholders and build professional relationships that support collaboration.
Identify potential issues and develop controls to mitigate risk.
Research advances in data science and artificial intelligence to support business analytics.
Develop advanced technical documentation for internally and vendor-developed models.
Work with developers to understand models, challenge methodologies, and ensure results are accurate.
Partner with technology teams and model users to schedule deployments and plan future model installations.
Work with independent model risk management, legal, and compliance teams to ensure models are validated and approved for use.
Produce analytics to check whether early model results are consistent with expectations.
Conduct regular model monitoring and share performance results and analytical insights with model stakeholders and users.
Support Bank policy and governance requirements for AI models and identify and mitigate risks associated with advanced techniques.
Track post-deployment model changes and ensure documentation reflects adjustments, patches, or updates.
Conduct model performance analytics beyond Model Risk Management policy requirements, including granular monitoring, early trend detection, root-cause analysis, and gap analysis.