Fraud Data Scientist.

• Would you like to play a leading role in a team whose ambition is to become a world class fraud function, exceptional at developing talent and turning information into insights?
• Do you enjoy collaborating with cross functional teams and influencing business direction with data-backed evidence?
• Do you actively seek opportunities for innovation and continuous improvement?

What Is The Role

We are looking for a technically strong Fraud Data Scientist to join the fraud decisioning capability within AIB. This role will focus on applying data science techniques to fraud detection and prevention in financial transactions, including payments and transfers, while also supporting forward-looking analytical insight across the fraud environment, * Apply domain knowledge in financial fraud to review and enhance existing anomaly detection in payment systems, including business rules and machine learning models.

• Support the transformation of new data streams into fraud risk signals to be used by rules and models.
• Develop a thorough understanding of the data science lifecycle including data exploration, preprocessing, feature engineering, modelling, validation, and deployment.
• Design, build, and maintain predictive models, including decision trees, random forests, and gradient-boosted trees, with a low-level understanding of their algorithms and functioning.
• Conduct A/B testing and other validation techniques to ensure the accuracy and reliability of payment rules and models.
• Communicate complex data insights to non-technical stakeholders through clear and actionable reporting.
• Collaborate with cross-functional teams and support data-driven improvements through exploration, feature engineering, and model enhancement, * Customer First
• Ensures Accountability
• Collaborates
• Eliminates Complexity
• Data Analysit
• Investigating & Reporting

• 3-5 years’ experience working with machine learning-based detection systems including development, validation, deployment, and post-live monitoring.
• In-depth knowledge of machine learning algorithms, particularly tree-based models, and anomaly detection performance KPIs.
• Hands-on expertise in SQL, Python, and Big Data tools such as Databricks.
• Understanding of fraud typologies such as card fraud, payment fraud, account takeover, and mule activity would be desirable.
• Exposure to fraud platforms such as Featurespace, TSYS, or similar detection systems is desirable; familiarity with graph database technologies such as Neo4j or TigerGraph is a plus.
• Ability to translate data into clear, business-focused insights and work effectively with a wide range of stakeholders.

Some Of Our Benefits Include

• Market leading Pension Scheme
• Healthcare Scheme
• Variable Pay
• Employee Assistance Programme
• Family leave options
• Two volunteer days per year