Head of Data Science & AI | Direct & Digital Insurance - Johannesburg

Job Description

• 10-15+ years of experience in Data Science, Advanced Analytics, AI, Machine Learning, or related fields. 5-8+ years in a leadership role managing data science teams and delivering enterprise-scale analytics solutions. Proven experience within: Insurance preferably short-term/direct insuranceFinancial Services.
• Digital platforms or customer-centric businessesThe role will be responsible for building and operationalising machine learning and AI models, the Head: Data Science drives experimentation and innovation across telematics, risk modelling, and customer decisioning including customer segmentation and client lifetime value.
• The role positions Absa Insurance at the forefront of digital insurance innovation and is explicitly distinct from Management Information and reporting functions. Master's level in Data Science, Statistics, Mathematics, Computer Science, Engineering.
• MBA or equivalent business qualification.

Professional certifications such as

• AWS Certified Machine Learning
• Microsoft Azure AI Engineer
• Google Professional Machine Learning Engineer
• SAS Advanced Analytics Certification

Job Description

• The role will be responsible for building and operationalising machine learning and AI models, the Head: Data Science drives experimentation and innovation across telematics, risk modelling, and customer decisioning including customer segmentation and client lifetime value. The role positions Absa Insurance at the forefront of digital insurance innovation and is explicitly distinct from Management Information and reporting functions.

Telematics

• Build driver behaviour models that predict risk and reward safe driving.
• Use connected-device data e.g., vehicle sensors, IoT geysers to enable proactive risk management.
• Translate raw telematics data into underwriting insights and customer value propositions.

Risk Modelling

• Predictive Underwriting: Apply AI/ML to assess claim probability upfront telematics, geospatial risk, external data to sharpen risk selection.
• Portfolio Stress Signals: Monitor book performance with models for lapse/NTU risk, persistency, and concentration exposures, providing early warning to complement actuarial reserving.

Customer Decisioning

• Develop models for customer segmentation, targeting, and personalised offers.
• Predict client lifetime value CLV to optimise acquisition and retention investments.
• Support decision engines for next-best action, pricing, and cross-sell in digital channels.

Education

Bachelor`s Degrees and Advanced Diplomas: Physical, Mathematical, Computer and Life Sciences Required