Manager: Fraud Data Insights and Analytics at Absa Group Limited (Absa)

Key Accountabilities

Data Analytics & Insights 

• Develop and implement data analytics frameworks to identify, quantify, and monitor fraud risk trends across Business Banking products and digital platforms. 
• Produce actionable fraud insights, dashboards, and MI for senior management and fraud committees. 
• Conduct deep-dive root-cause and loss analytics to support strategic decision-making. 
• Partner with Fraud Operations to identify control weaknesses and recommend data-informed improvements. 
• Design and maintain data models to track key metrics such as fraud losses, recovery rates, and prevention ROI. 

Advanced Analytics & Modelling 

• Apply predictive analytics and machine learning to detect anomalous behaviour, identify emerging fraud threats, and enhance early-warning systems. 
• Collaborate with data science teams to develop, test, and calibrate fraud risk models. 
• Evaluate performance of existing rules and models, ensuring optimal detection vs. false-positive rates. 
• Support digital and product teams with data-driven fraud control design for new initiatives. 

Fraud Intelligence & Reporting 

• Manage end-to-end fraud data collection, validation, and integrity across systems. 
• Build automated fraud reporting pipelines (Power BI, Tableau, or other visualization tools). 
• Translate complex data into clear narratives and visual storytelling for business and executive audiences. 
• Contribute to monthly, quarterly, and ad hoc fraud performance reports to committees and regulators. 

Collaboration & Stakeholder Management 

• Partner with internal stakeholders (Fraud Strategy, Fraud Operations, Business Banking Product Heads, Data & Analytics teams) to ensure a unified data approach. 
• Support governance and risk functions with fraud data for audits, risk assessments, and regulatory submissions. 
• Build strong relationships with Group Data, IT, and Cyber teams to align on data standards and security. 

Continuous Improvement 

• Stay current with industry trends, analytics techniques, and fraud typologies. 
• Lead or participate in data innovation projects – e.g., behavioural biometrics, network analytics, or AI-driven detection. 
• Mentor analysts and develop the team’s analytical capability. 
• Contribute to the strategic fraud roadmap by identifying new opportunities for data-led efficiencies.

Preferred Education 

• Bachelor’s degree in Data Science, Statistics, Mathematics, Computer Science, Economics, or Risk Management. 
• Postgraduate qualification (MSc, MBA, or equivalent) advantageous. 
• CFE (Certified Fraud Examiner) advantageous 
• Data Analytics Certifications (SAS, SQL, Python, R, Power BI) 
• Machine Learning or AI certifications (AWS, Google, Microsoft) 

Preferred Experience 

• 7–10 years’ experience in data analytics, business intelligence, or fraud analytics (preferably in financial services or business banking). 
• Proven track record in data modelling, dashboard design, and analytical problem-solving. 
• Exposure to fraud risk management frameworks, digital banking, and payments ecosystems. 
• Experience using big data environments (e.g., Hadoop, Spark, Databricks) and cloud analytics platforms.