Credit Risk Data Scientist for Cashflow Analytics

pave; Los Altos (CA); On-site; USD 120,000 - 180,000; Full time

Job summary

Pave is seeking a data scientist to build and optimize cashflow-driven credit risk models in the US fintech space. You will design, evaluate, and productionize models that demonstrate the impact of cashflow scores and attributes on approvals and defaults, collaborating with data engineers and stakeholders.

Applicants should have strong data science skills, experience with scikit-learn and XGBoost, and a deep understanding of US credit risk practices.

Qualifications

• Strong analytical and data exploratory skills and the ability to translate data into actionable insights.
• Experience from data analysis to building high-performing ML models, including feature engineering.

Responsibilities

• Develop and maintain models (ML-based or heuristic) to enhance product offerings.
• Analyze the impact of Pave scores and attributes on customer performance metrics, aiming to increase approvals and reduce defaults.
• Design, implement, and evaluate experiments to test new attributes and models.
• Collaborate with data engineers to deploy models, monitor performance, and update for accuracy.
• Communicate findings and recommendations to stakeholders through reports, dashboards, and presentations.
• Stay current with advances in data science, AI/ML, and credit risk analytics tools and techniques.
• Translate fair lending considerations into model attributes and analyses for credit risk.

Skills

Data analysis

ML modeling

Experiment design

Stakeholder communication

Tools

scikit-learn

XGBoost

Job description

Pave is seeking a data scientist to build and optimize cashflow-driven credit risk models in the US fintech space. You will design, evaluate, and productionize models that demonstrate the impact of cashflow scores and attributes on approvals and defaults, collaborating with data engineers and stakeholders.

Applicants should have strong data science skills, experience with scikit-learn and XGBoost, and a deep understanding of US credit risk practices.