Data Scientist (Payments Risk Analytics)

Your Mission

We are looking for a Risk & Payments Intelligence Analyst to join our Risk & Fraud team. In this role, you will analyze data related to ACH transactions, ML risk scores, risk rules, decisioning systems, and vendor data to understand performance, surface emerging trends, and inform ongoing optimization of payment program decisions. This role focuses on portfolio and system level analysis rather than case-by-case transaction review or manual queues, and requires strong analytical judgment in ambiguous, data-constrained environments, including the evaluation of new data, analytical methods, and AI-assisted approaches as our risk capabilities evolve.

Key Responsibilities

• Analyze end-to-end ACH payment decisioning performance, including ML risk scores and risk rules, across approvals and losses.
• Detect and analyze emerging trends in customer behavior, payment outcomes, and risk signals.
• Evaluate how changes in strategies, data, or rules impact downstream decisioning and outcomes over time.
• Independently define analytical questions, assemble datasets from multiple sources, and iterate toward insights without predefined reporting templates.
• Use Python to perform exploratory data analysis, feature evaluation, cohort analysis, and experimentation across large ACH and risk datasets.
• Develop repeatable analytical workflows and lightweight tooling in Python to accelerate insight generation and reduce manual analysis overhead.
• Perform ad hoc analyses to evaluate the value and usefulness of new or existing data signals for risk decisioning.
• Design analyses and reporting that support ongoing risk reviews, strategy discussions, and portfolio-level monitoring.
• Explore and apply established and emerging analysis techniques to accelerate insight generation, trend detection, and decision support within regulated risk and payment datasets.
• Partner with Risk, Product, and Relationship Management teams to inform strategy refinement and prioritization.
• Communicate trends, findings, and recommendations clearly to internal stakeholders and, when applicable, external clients.
• Work with large, imperfect, and regulated datasets to form actionable conclusions despite data gaps, latency, or attribution challenges.