The Global Risk Solutions and Strategy group is a fast-growing team optimizing risk solutions and models, and we are a key function to help enable WEX’s strategic objectives. The Risk Solutions Team employs data science methodologies (machine learning and statistical frameworks), a wide suite of data types, and modern technologies to develop solutions to inform decision making. Our team helps the firm identify and measure credit and fraud risk to proactively manage the risk throughout the client’s life-cycle. As such, you will not only be working with the latest data and machine learning technologies and algorithms, you will be working in a dynamic environment alongside our stakeholders and domain experts to build models and drive better decision-making.
About the Team/Role
Partner with stakeholders to understand credit risk management requirements and translate them into data-driven solutions to measure and monitor credit risk across the firm’s products and services.
Proactively identify and communicate challenges, opportunities, and risks associated with end-to-end model development and deployment life-cycle to ensure timely completion of the entire product.
Leverage advanced machine learning, artificial intelligence, and statistical methods and technologies to design flexible, scalable, and automated risk modeling solutions.
Develop and review code and automated processes to extract credit risk patterns from large scale application and transaction data, behavioral patterns, and other risk indicators.
Keep abreast with emerging trends in machine learning and identify opportunities to leverage new tools to solve problems and improve processes.
Mentor and support junior data scientists, sharing knowledge and best practices to elevate the data science practice at WEX.
How you'll make an impact
Insights Driven: Clear hypothesis and objective driven analytics that help drive our business decisions and ongoing metrics
Stakeholder Aligned: Understand the needs and audience for deliverables with a succinct and tailored message to maximize impact
Results Focused: Rigorous focus on how analytics drive the end to end experiences with clear path to production and measurable impact
Dynamic Collaboration: Drive continual improvement of our team best practices and processes to power collaboration
Quality Mindset: Trust in our findings is critical so data and analytic quality is understood and accounted for from the beginning
Curiosity and Learning: Learn new technologies and collaborate and teach others how to use them as necessary.
4 or more years of professional experience in data science, machine learning, and artificial intelligence, with a focus on credit risk management in underwriting, behavioral surveillance, and loss prevention in the financial services industry.
Master’s or Ph.D. degree in a quantitative field such as Mathematics, Statistics, Data Science, Operations Research, Computer Science.
Strong knowledge of credit risk-drivers in small and medium sized businesses, public firms, and private firms, including data typically used in credit risk management from external credit bureaus and internal risk management processes
Advanced knowledge of SQL and experience creating and managing large datasets to organize and extract useful information
Advanced knowledge of Python or R and experience with common data science libraries such as lightgbm, scikit-learn, pandas, etc..
Deep understanding of model deployment requirements for scalable solutions and real-time feature stores
Deep expertise in statistical and machine learning techniques, including modeling, testing and inference, sampling methods, supervised and unsupervised learning.
Strong communication and presentation skills with an ability to relate complex analytics findings to business outcomes
Adaptable and comfortable working collaboratively and independently in a self-starting manner
Evidence of creative problem solving, critical thinking and a continual learning mindset in credit risk management.
Prior experience mentoring experience of data scientists
Prior roles responsible for building underwriting and behavioral models.
Knowledge of external intelligence sources, including third-party data providers e.g. LexisNexis, Socure, Dun and Bradstreet
Experience using cloud environments to develop advanced models, such as AWS Sagemaker
Experience with end–to-end machine learning systems and MLOps framework