Data Scientist – Credit Analytics
About the Role
We are looking for a Data Scientist – Credit Analytics to build, analyze, and optimize credit risk models that support Electrum’s financing, rent-to-own, and partner credit programs. In this role, you will work closely with Risk, Finance, Product, and Operations teams to translate data into actionable insights that drive better credit decisions, portfolio performance, and customer outcomes.
You will play a key role in developing data-driven frameworks for credit scoring, approval, monitoring, and loss mitigation across Electrum’s ecosystem.
What You Will Do
Credit Modeling & Analytics
Develop and maintain credit scoring models, risk segmentation, and decision frameworks.
Analyze customer, transaction, and behavioral data to assess creditworthiness and default risk.
Build and validate predictive models for approval rate, delinquency, default, and recovery.
Monitor portfolio performance metrics such as NPL, PD, LGD, ECL, and vintage analysis.
Data Analysis & Insights
Conduct deep-dive analyses to identify drivers of credit performance and risk trends.
Perform cohort, funnel, and behavioral analysis to improve underwriting and credit policy.
Translate complex data findings into clear insights and recommendations for stakeholders.
Support A/B testing and experimentation for credit rules, pricing, and policy changes.
Risk Strategy & Decision Support
Partner with Risk and Business teams to define credit policies, cut-offs, and eligibility rules.
Provide data support for credit strategy initiatives including limit setting, pricing, and collections.
Design dashboards and monitoring tools to track portfolio health and early warning indicators.
Data Engineering & Governance
Work with Data Engineering teams to ensure data quality, availability, and reliability.
Define data requirements, feature engineering logic, and data documentation standards.
Ensure compliance with data governance, privacy, and regulatory standards.
What You Bring
Bachelor’s or Master’s degree in Data Science, Statistics, Mathematics, Economics, Engineering, or related field.
2–5 years of experience in credit analytics, risk modeling, or financial data science.
Strong proficiency in Python or R for data analysis and modeling.
Solid understanding of statistical modeling, machine learning, and predictive analytics.
Experience working with structured datasets (SQL, data warehouses).
Knowledge of credit risk concepts such as PD, LGD, EAD, NPL, IFRS 9 / PSAK 71 is a strong advantage.
Ability to clearly communicate insights to non-technical stakeholders.
Nice to Have
Experience in fintech, lending, BNPL, rent-to-own, or consumer finance.
Familiarity with alternative data sources (telemetry, transactional, behavioral data).
Experience with BI tools (Looker, Tableau, Power BI).
Exposure to model governance, validation, or regulatory reporting.