Senior Data Scientist, Fraud Risk Strategy & Analytics

Role Summary\nSenior Data Scientist focused on fraud strategy analytics and operational monitoring across a consumer lending portfolio. You will turn fraud data, scorecard performance, and decisioning outcomes into actionable policy, rule, and reporting recommendations — partnering closely with fraud operations, product, credit/risk, data engineering, and external vendors. Day-to-day responsibilities include monitoring, trend detection, third-party signal assessment, and cross-functional execution.\n\nKey Responsibilities\nTranslate fraud data and model outputs into clear policy, rule, and threshold recommendations for the decision engine, and partnering with cross-functional teams to prioritize and implement them.\nMonitor portfolio fraud performance — loss rates, capture rates, false-positive rates, approval impact, vintage trends, and segment-level KPIs — and surface issues with proposed actions.\nTrack scorecard and model performance (PSI, score drift, KS, decay) and recommend recalibration, rule adjustments, or escalation when performance degrades.\nDetect emerging fraud trends, rings, and cross-channel vulnerabilities through analytics on application, behavioral, device, and third-party data; size the impact and propose mitigations.\nAssess and benchmark third-party fraud and identity signals (identity verification, device intelligence, consortium data, bank/transaction data); recommend which to onboard, retire, or reweight.\nPartner with fraud operations to monitor real-time fraud trends, interpret investigator findings, and convert case-level insights into rule, policy, and reporting changes.\nDesign and analyze champion/challenger tests and policy backtests to quantify the impact of strategy changes on fraud rates, approvals, and downstream credit performance.\nProduce regular fraud reporting and executive deep dives — loss attribution, typology trends, decisioning outcomes — for senior leadership.\nCollaborate with product, data engineering, credit/risk, and external vendors to evolve fraud data sources, decisioning workflows, and monitoring infrastructure.\nAct as a subject matter expert on fraud data, scorecard behavior, and decision engine outcomes for cross-functional partners.\n\nQualifications\n4–7 years in fraud strategy and analytics in financial services or fintech, with a hands-on analytical focus.\nStrong understanding of fraud typologies in consumer lending — identity, synthetic, first-party, and third-party fraud — and how they manifest in application and account data.\nWorking knowledge of fraud models and scorecards: how they are built, evaluated, and monitored, with the ability to interpret outputs and recommend strategy changes.\nAdvanced SQL and Python proficiency for portfolio analytics, segmentation, and reporting.\nExperience working with third-party fraud data providers and integrating fraud rules or signals into decision engines.\nClear written and verbal communication; able to translate analytics into recommendations for technical and non-technical stakeholders.\nBachelor’s degree in a quantitative field (Statistics, Economics, Mathematics, Computer Science, Engineering, or related).\n\nPreferred Qualifications\nExperience in consumer lending or other high-fraud-risk credit products.\nFamiliarity with US consumer lending regulations and risk management practices.\nExposure to graph or network analysis for fraud ring detection.