- Company Name
- Achieve
- Job Title
- Sr. Data Scientist (Credit Risk)
- Job Description
-
**Job Title**
Sr. Data Scientist (Credit Risk)
**Role Summary**
Develop, maintain, and enhance credit risk models for lending portfolios, translating data insights into actionable business guidance. Lead model monitoring, forecasting, and reporting while ensuring audit‑ready documentation and governance compliance.
**Expectations**
- Deliver accurate loss forecasts and scenario analyses for portfolio segments.
- Communicate model performance and emerging risks to stakeholders (Capital Market, Marketing, risk governance).
- Automate pipelines, dashboards, and reporting to improve efficiency and accuracy.
- Provide analytical support for credit policy decisions and pricing optimization.
- Maintain audit‑ready documentation and participate in external reviews.
**Key Responsibilities**
1. Build and maintain credit risk models (scorecards, XGBoost, survival analysis, vintage models).
2. Extract, clean, and manipulate large datasets using SQL and Python; construct pipelines and analytics for model and portfolio monitoring.
3. Conduct exploratory data analysis to identify portfolio trends, loss drivers, and model deviations.
4. Produce monthly/quarterly loss forecasts by vintage and segment; perform stress tests, scenario analyses, and sensitivity testing.
5. Automate reporting, dashboards, and pipeline monitoring.
6. Document methodologies, assumptions, data sources, and results in audit‑ready format.
7. Support model validation, governance, and liaise with external auditors or regulators.
8. Identify process, modeling, and infrastructure improvement opportunities.
**Required Skills**
- 3+ years in credit risk modeling and portfolio monitoring (charge‑offs, delinquencies, vintage, roll‑rate analysis).
- Advanced programming in Python and SQL for data analysis, modeling, and automation.
- Strong foundation in probability, statistics, and machine‑learning techniques.
- Experience with scorecard, XGBoost, time‑series, vintage modeling, survival analysis, or logistic regression in consumer credit.
- Proficiency in data visualization/dashboards (Tableau, Python widgets).
- Excellent analytical, critical‑thinking, and communication skills.
- Documentation expertise for audit‑ready deliverables (methodologies, assumptions, validation).
**Required Education & Certifications**
- Master’s degree in Economics, Statistics, Mathematics, Data Science, or related quantitative discipline (PhD preferred but not required).