Actuarial Data Scientist

HALA is a leading fintech player in the MENAP region that aims to redefine financial services and build the future bank of SMEs. HALA aims at empowering SMEs to start, run, and grow their businesses by providing them with cutting-edge financial and technological tools.

HALA currently holds multiple entities in UAE, Saudi Arabia and Egypt (including HALA Payments and HALA Logistics) and offers solutions that enable merchants to digitize their payments as well as manage their sales and operations.

Founded in 2017, HALA is currently licensed by the Saudi Arabian Central Bank.

Company: Hala Financing
Team: Data & Business Intelligence
Location: Riyadh, Saudi Arabia
Employment Type: Full-time

Hala Financing is looking for an Actuarial Data Scientist to join the Data team and support the development of our credit engine, risk models, and portfolio monitoring capabilities.

The role will focus on predicting probability of default, improving credit decisioning, enhancing risk segmentation, and building data-driven models that support responsible growth in SME lending. The ideal candidate combines actuarial thinking, credit risk modelling, machine learning, and strong business judgment.

• Build, validate, and improve models for probability of default, credit scoring, affordability, delinquency prediction, and customer risk segmentation.

• Analyze historical repayment behavior, first-payment failure, delinquency trends, vintage curves, and default patterns.

• Support the enhancement of Hala Financing’s credit engine by identifying stronger predictive variables and decision rules.

• Develop early-warning indicators to detect customers likely to delay, default, or underperform.

• Monitor portfolio performance across cohorts, channels, customer segments, loan products, tenure, ticket size, and repayment behavior.

• Build dashboards and analytical frameworks to track approval quality, disbursement performance, default rates, roll rates, collections performance, and portfolio risk.

• Run scenario analysis and stress testing to assess the impact of growth, pricing, approval policy, and macroeconomic changes on portfolio performance.

• Support management reporting for credit performance, investor reporting, and internal risk committees.

• Use statistical and machine learning techniques to improve credit decisioning and default prediction.

• Work with structured and alternative data sources, including transaction data, merchant behavior, repayment history, business activity, and external data where available.

• Design experiments and champion/challenger tests to evaluate credit policy changes.

• Partner with Data Engineering to improve data quality, feature availability, model monitoring, and automation.

• Work closely with Credit, Risk, Product, Collections, Finance, and Business teams to translate business questions into analytical solutions.

• Provide clear recommendations on credit policy, approval rules, risk appetite, and portfolio growth.

• Help balance growth, profitability, and risk by turning data insights into practical business actions.

• Bachelor’s degree in Actuarial Science, Statistics, Mathematics, Data Science, Computer Science, Engineering, Finance, or a related quantitative field; Master’s degree preferred.

• 3–6 years of experience in actuarial analytics, credit risk, lending analytics, banking, fintech, insurance, or financial modelling.

• Strong understanding of probability of default, credit scoring, portfolio risk, delinquency, loss forecasting, and cohort/vintage analysis.

• Strong skills in Python and SQL.

• Experience with statistical modelling, machine learning, regression, classification models, decision trees, gradient boosting, model validation, and performance monitoring.

• Ability to translate complex analytical findings into simple business recommendations.

• Strong communication skills and ability to work with both technical and non-technical stakeholders.

• Improved accuracy of default prediction and credit risk segmentation.

• Reduced first-payment failure and early delinquency rates.

• Stronger credit engine decisioning and approval quality.

• Clear portfolio monitoring and early-warning indicators.

• Better balance between loan growth, risk, profitability, and capital efficiency.