1. Job Summary
We are seeking a Data Scientist to design, build, and optimize machine learning-based credit and fraud risk models across our consumer lending and
BNPL product lines. This role involves end-to-end ownership of model development - from data exploration and feature engineering to model training, validation, deployment, and performance monitoring - to enable data-driven decisioning across markets.
2. Key Responsibilities
A. Credit & Fraud Risk Modeling
- Develop, refine, and maintain statistical and machine learning models for credit risk scoring, fraud detection, customer lifecycle prediction, and product performance forecasting.
- Perform deep analysis of large-scale structured and unstructured datasets (e.g., internal behavioural data, credit bureau data, mobile/device signals, e-commerce data).
- Engineer and evaluate large numbers of predictive features to improve model accuracy, stability, and robustness.
B. Data Pipeline & Model Deployment
- Build and optimize data pipelines for model development and production deployment.
- Validate and monitor data quality, feature stability, rank ordering, and score performance across multiple data sources.
- Collaborate with engineering teams to integrate models into production systems (API development, UAT testing, usage monitoring).
C. Analytics & Insights
- Conduct exploratory data analysis (EDA) to uncover business insights and support product/policy decisions.
- Design and run A/B tests to measure model impact and evaluate new credit and fraud strategies.
- Prepare dashboards and reporting frameworks for business and risk stakeholders.
D. Stakeholder Collaboration
- Work closely with product, business, engineering, data, and compliance teams to refine requirements and ensure model alignment with business objectives.
- Provide risk insights and analytical recommendations to enhance overall portfolio performance.
E. Governance & Documentation
- Produce comprehensive model documentation, validation reports, and monitoring materials in line with internal governance and regulatory expectations.
- Ensure all model changes and deployments follow established governance and audit requirements.
3. Required Qualifications
- Bachelor's degree in Statistics, Computer Science, Data Science, Mathematics, Engineering, or related fields.
- 2-5+ years of experience in data science, quantitative analytics, or machine-learning model development.
- Practical experience in:
- Python, SQL, feature engineering
- Machine learning techniques (e.g., logistic regression, XGBoost, random forest, scorecards)
- Model validation, monitoring, and A/B testing
- Data pipeline design and production deployment
4. Preferred Qualifications
- Experience in consumer lending, BNPL, credit bureau, or digital banking risk analytics.
- Familiarity with model governance frameworks, credit policy, or fraud risk management.
- Experience building automated data workflows or reusable modeling packages.
5. Key Competencies
- Strong analytical reasoning and statistical skills
- Ability to translate data insights into actionable business recommendations
- Detail-oriented with strong model documentation capability
- Collaborative, with excellent stakeholder communication skills
