Credit Risk Modelling Data Scientist

About HALA Financing

HALA Financing, a dynamic fintech enterprise within the HALA Group, is at the forefront of transforming financial services across the MENAP region. Our mission is to empower small and medium-sized enterprises (SMEs) by providing them with innovative financial and technological solutions that enable seamless business operations. As part of a rapidly expanding ecosystem that includes HALA Payments and HALA Logistics, we offer cutting-edge tools for digital payments, sales management, and operational efficiency. Established in 2017 and licensed by the Saudi Arabian Central Bank, HALA Financing is committed to driving responsible growth in SME lending through data-driven decision-making and advanced risk management.

Position Overview

We are seeking a highly analytical and strategic Credit Risk Modelling Data Scientist to join our Data & Business Intelligence team in Riyadh, Saudi Arabia. This role will play a pivotal part in enhancing our credit engine, refining risk models, and strengthening portfolio monitoring capabilities. The ideal candidate will possess a unique blend of actuarial expertise, credit risk modelling proficiency, and machine learning acumen, coupled with a keen business acumen to drive informed decision-making. Your work will directly contribute to Hala Financing’s mission of fostering sustainable growth in SME lending while maintaining robust risk management practices.

Key Responsibilities

Credit Risk Modelling

• Develop, validate, and refine predictive models for critical risk metrics, including probability of default, credit scoring, affordability assessments, delinquency prediction, and customer risk segmentation.
• Analyze historical repayment behaviors, first-payment failure rates, delinquency trends, vintage curves, and default patterns to uncover actionable insights.
• Collaborate with cross-functional teams to enhance Hala Financing’s credit engine by identifying and integrating stronger predictive variables and decision rules.
• Design and implement early-warning systems to proactively identify customers at risk of delayed payments, default, or underperformance.

Portfolio Analytics

• Monitor and evaluate portfolio performance across diverse dimensions, including customer cohorts, sales channels, risk segments, loan products, tenure, ticket sizes, and repayment behaviors.
• Develop and maintain dynamic dashboards and analytical frameworks to track key performance indicators such as approval quality, disbursement efficiency, default rates, roll rates, collections performance, and overall portfolio risk.
• Conduct rigorous scenario analyses and stress testing to assess the potential impact of growth strategies, pricing adjustments, approval policy changes, and macroeconomic fluctuations on portfolio health.
• Support management reporting initiatives, including credit performance evaluations, investor reporting, and risk committee presentations.

Data Science & Machine Learning

• Leverage advanced statistical and machine learning techniques to elevate credit decisioning processes and enhance default prediction accuracy.
• Work with a diverse range of data sources, including transactional data, merchant behavior analytics, repayment histories, business activity metrics, and external data feeds where applicable.
• Design and execute experiments, including champion/challenger tests, to rigorously evaluate the effectiveness of credit policy modifications.
• Partner closely with Data Engineering teams to improve data quality, expand feature availability, implement robust model monitoring systems, and automate analytical workflows.

Business Partnership

• Collaborate effectively with Credit, Risk, Product, Collections, Finance, and Business teams to translate complex business challenges into data-driven solutions.
• Provide strategic recommendations on credit policy adjustments, approval rule refinements, risk appetite frameworks, and portfolio growth strategies.
• Balance the triad of growth, profitability, and risk by converting analytical insights into actionable business strategies that align with organizational objectives.

Qualifications & Requirements

• Bachelor’s degree in Actuarial Science, Statistics, Mathematics, Data Science, Computer Science, Engineering, Finance, or a closely related quantitative discipline; a Master’s degree is highly desirable.
• 3 to 6 years of hands-on experience in actuarial analytics, credit risk management, lending analytics, banking, fintech, insurance, or financial modelling.
• Deep understanding of core credit risk concepts, including probability of default, credit scoring methodologies, portfolio risk assessment, delinquency forecasting, loss forecasting, and cohort/vintage analysis.
• Proficiency in Python and SQL, with a strong foundation in statistical modelling, machine learning algorithms, regression analysis, classification models, decision trees, gradient boosting, model validation, and performance monitoring.
• Exceptional ability to distill complex analytical findings into clear, concise, and actionable business recommendations for stakeholders at all levels.
• Strong problem-solving skills, intellectual curiosity, and a passion for leveraging data to drive strategic business outcomes.