Fraud Data Scientist: AI Scores & Models (4‑Day Office)

Equifax, Inc.; City Of London; Hybrid; GBP 90,000 - 130,000; Full time

Benefits offered by this job

4 days in-office collaboration (Mon-TH

Friday flexibility

Job summary

Equifax UK Data & Analytics is seeking a data scientist to develop market leading fraud models and scores. You will use consumer and commercial bureau data, apply ML/AI techniques, and leverage cloud platforms to deliver predictive solutions.

You will collaborate with product, risk, and data teams to refine models and ensure robust deployment, documenting processes for governance and review.

Qualifications

• Experience using credit bureau data in statistical fraud models.
• Extensive experience developing statistical models and scores in fraud (consumer and commercial).
• Strong numerical ability with a relevant degree 2:1 or above.
• Proficient in Python, SAS, BigQuery, Jupyter Notebook, SQL on a daily basis.
• Experience developing regression models and scores (e.g., logistic).
• Familiarity with large/complex datasets and data extraction from multiple platforms.

Responsibilities

• Develop market leading statistical fraud models and scores using diverse data sources.
• Apply traditional and AI/ML techniques (logistic regression, gradient boosting, random forests).
• Utilise cloud based technologies and analytics tooling for test-and-learn approaches.
• Create new features to improve predictive power of models.
• Collaborate with stakeholders to deliver new scores and products.
• Document development processes for peer review and risk management.

Skills

Python

SAS

SQL

Jupyter Notebook

BigQuery

ML/AI techniques

Education

Numerate degree 2:1 or above

Tools

GCP

Vertex AI

Job description

Equifax UK Data & Analytics is seeking a data scientist to develop market leading fraud models and scores. You will use consumer and commercial bureau data, apply ML/AI techniques, and leverage cloud platforms to deliver predictive solutions.

You will collaborate with product, risk, and data teams to refine models and ensure robust deployment, documenting processes for governance and review.