Job Summary
The role involves the development of predictive and causal models aimed at enhancing borrower repayment performance. The position focuses on assessing servicing strategies, including loan modifications and payment assistance programs. The successful candidate will collaborate with Product, Engineering, and Servicing and Collections Operations to translate analytical findings into actionable operational decisions that improve payment experiences and communications.
Responsibilities
- Design and implement predictive and causal models to support improved borrower repayment outcomes.
- Evaluate various servicing interventions, such as loan modifications and payment assistance efforts.
- Translate model results into practical operational strategies through collaboration with cross-functional teams.
- Work closely with various departments on enhancing payment experiences, communication strategies, collections methodology, and evaluating agent performance.
Qualifications
- A graduate degree in a quantitative discipline is essential.
- Minimum of two years of experience in machine learning, statistical modeling, or applied quantitative research is required.
- Proficiency in Python for production-quality coding is mandatory.
- Experience with causal inference and experimentation related to real-world applications is necessary.
- A PhD and familiarity with payment products, treatment-effect modeling, and the development of production models are highly preferred.
