Fraud Strategy & Modeling Senior Manager

Role SummaryWe are seeking a Fraud Strategy & Modelling Senior Manager to lead the development and optimization of fraud risk strategies across both consumer and SME lending products at Botim.This role sits at the intersection of fraud strategy, advanced analytics, and real‑time decisioning, with responsibility for building scalable fraud controls across the full customer lifecycle — from onboarding and application screening to transaction monitoring and post‑disbursement behaviour.The ideal candidate will bring hands‑on experience in fraud modelling and rule‑based strategy design, with a strong understanding of credit lending fraud, real‑time decision systems, and modern fraud tooling. You will play a critical role in balancing fraud prevention, approval rates, and customer experience within a high‑growth fintech environment.ResponsibilitiesOwn the design and optimisation of fraud strategies and rules across onboarding, application, underwriting, disbursement, and transaction monitoring.Develop and manage real‑time fraud decisioning logic within rule engines and decision platforms.Continuously optimise fraud controls through rule tuning, segmentation, and back‑testing to minimise false positives and maximise fraud capture.Partner with Data Science teams (and remain hands‑on where needed) to build, deploy, and monitor fraud detection models (e.g. XGBoost, LightGBM, ML‑based classifiers).Develop and evaluate models using metrics such as AUC, KS, precision/recall, PSI, false‑positive rate, and fraud capture rate.Perform deep‑dive analysis on fraud patterns using transaction data, behavioural signals, device data, and customer attributes.Identify and mitigate key fraud risks including application fraud/document fraud, identity & synthetic identity fraud, account takeover, mule accounts & network fraud (link analysis), first‑party/bust‑out fraud.Leverage network/link analysis and behavioural analytics to detect coordinated fraud activity.Support integration of internal and external data sources including bureau data, device intelligence, behavioural data, and third‑party fraud tools.Work with Engineering to ensure fraud strategies are embedded into scalable, low‑latency decisioning systems.Contribute to building fraud data marts, pipelines, and monitoring frameworks.Partner closely with Risk, Product, Engineering, Data Science, Operations, and Fraud Investigation teams.Translate fraud insights into business decisions and product improvements.Support the build‑out of fraud governance, reporting, and policies for a growing lending business.RequirementsBachelor’s degree in Data Science, Statistics, Mathematics, Computer Science, Finance, or related field.5–8+ years of experience in fraud strategy, fraud analytics, or fraud modelling within fintech, lending, payments, or banking.Strong hands‑on experience with Python and SQL, machine learning models (e.g. XGBoost, LightGBM, logistic regression).Experience developing and deploying fraud models in production environments.Strong understanding of model monitoring and stability metrics such as PSI, CSI, feature drift, etc.Experience designing and optimising fraud rules and decision strategies.Hands‑on experience with fraud decisioning tools / rule engines (e.g. DataVisor, Unit21, Forter, or similar).Familiarity with transaction monitoring systems, AML/fraud alerts, and case management workflows.Strong understanding of fraud risks across consumer lending and/or SME lending, customer onboarding and KYC flows, transaction and behavioural fraud detection.Experience working with real‑time or near real‑time decision systems is highly preferred.Experience with link analysis / network fraud detection, explainable AI / SHAP / model interpretability, cloud environments (AWS/GCP) and data pipelines.Exposure to UAE/GCC or emerging markets fraud patterns is a plus.#J-18808-Ljbffr