Data Scientist
Job Description
Applied Data Scientist – Fraud Detection
\nContract: 6 months
\nEngagement: Inside IR35
\nLocation: Fully remote, with occasional travel to the London office.
\nThe Role
\nWe're looking for an experienced Applied Data Scientist to help improve the performance of our production fraud detection models.
\nWorking within our Fraud Intelligence team, you'll analyse large-scale datasets, identify new behavioural signals and optimise machine learning models to improve fraud detection accuracy while reducing false positives.
\nThis is a highly practical role suited to someone who enjoys working with complex data and delivering measurable improvements to live production models. You'll work closely with Machine Learning Engineers and Product teams to continually enhance the intelligence powering our fraud prevention platform.
\nResponsibilities
\nAnalyse large-scale fraud and transaction datasets.
\nEngineer new features to improve fraud detection performance.
\nOptimise production machine learning models.
\nImprove model performance against key metrics including F1 Score, Precision and Recall.
\nIdentify behavioural patterns associated with fraudulent activity.
\nAnalyse behavioural biometric and device intelligence data.
\nDesign and execute model evaluation experiments.
\nBuild Python-based analytical workflows.
\nWrite complex SQL against Azure Data Lake.
\nPresent recommendations based on statistical analysis.
\nWork closely with Machine Learning Engineers to transition successful improvements into production.
\nEssential Skills
\nCommercial experience as a Data Scientist or Applied Data Scientist.
\nStrong Python and Pandas.
\nAdvanced SQL.
\nExperience working with Azure Data Lake or similar cloud data platforms.
\nExperience working with very large datasets.
\nStrong feature engineering experience.
\nExperience improving production classification models.
\nExcellent understanding of F1 Score, Precision, Recall and model evaluation.
\nExperience working with highly imbalanced datasets.
\nDesirable
\nFraud detection.
\nFinancial crime.
\nPayments.
\nBanking.
\nBehavioural biometrics.
\nDevice intelligence.
\nTransaction monitoring.
\nRisk scoring.
