Lead - Fraud Analytics

About The Role
Our cleint a leading financial services brand is seeking a seasoned fraud analytics leader to own and drive the end-to-end fraud strategy for their digital lending portfolio. The role sits at the intersection of risk management, advanced analytics, and cutting-edge AI, and offers the opportunity to build next-generation fraud detection capabilities — from traditional rules and scorecards to LLM-powered agentic workflows. You will partner closely with Risk, Credit, Tech, Compliance, and external data providers to protect portfolio quality while enabling seamless customer experiences.
Key Responsibilities
Lead end-to-end Fraud Analytics strategy across all digital lending products, covering onboarding, underwriting, disbursement, and the repayment lifecycle.
Own fraud risk performance for the portfolio by monitoring key metrics such as FPD, EPD, fraud rates, and loss trends; ensure fraud losses remain within defined thresholds.
Design, develop, and continuously enhance fraud detection strategies leveraging rules engines,scorecards, statistical models, and advanced analytics techniques.
Lead the development and deployment of next-generation fraud detection capabilities using Generative AI, including LLM-powered workflows, Retrieval-Augmented Generation (RAG), and autonomous AI agents.
Conceptualize and implement agentic workflows to automate fraud investigation processes, anomaly detection, and signal generation at scale.
Drive innovation through use of synthetic data generation and simulation frameworks to identify emerging fraud typologies and stress-test fraud controls.
Define and implement fraud risk policies, underwriting rules, and approval frameworks to optimize customer experience while minimizing fraud risk.
Collaborate with business, partnerships, and external stakeholders to strengthen sourcing quality, improve underwriting frameworks, and enhance fraud prevention mechanisms.
Lead partnerships with external data providers (bureau, alternate data, device intelligence, telecom, etc.) and evaluate new data sources through pilots and POCs.
Drive deep-dive analytics on fraud incidents, emerging patterns, and channel-level risks; translate findings into actionable strategies, features, and rule enhancements.
Build and oversee scalable fraud data infrastructure, including feature marts and monitoring systems, in collaboration with Data Engineering, Tech, and DWH teams.
Define fraud KPIs, dashboards, and reporting frameworks for senior leadership, ensuring timely and actionable insights.
Lead cross-functional collaboration with FCU, Risk, Credit, Collections, Compliance, and Tech teams to drive fraud prevention initiatives and improve portfolio quality.
Present fraud insights, strategic recommendations, and performance updates to senior leadership and stakeholders.
Ensure compliance with regulatory guidelines, audit requirements, and internal risk governance standards.
Lead audit engagements, policy reviews, and hindsight analyses to continuously strengthen fraud frameworks.
Mentor and guide junior analytics team members, fostering analytical excellence and innovation within the team.
Education
Bachelor's degree in Engineering, Statistics, Mathematics, Economics, Computer Science, or a related quantitative field.
MBA / PGDM / Master's in Analytics, Data Science, or AI is a plus.
Work Experience
10+ years of experience in fraud analytics, risk analytics, or data science within BFSI / NBFC / FinTech.
Strong experience in unsecured digital lending products such as Personal Loans, Consumer Loans, BNPL, Credit Lines, or Cross-sell portfolios.
Proven experience in leading fraud strategy, policy design, and data-driven risk decisioning is essential.
Primary Skill
Deep expertise in fraud analytics and strategy across digital lending portfolios, with proven ability to design and deploy data-driven fraud prevention frameworks. Strong understanding of fraud typologies, risk policies, and portfolio performance management.
Technical Skills
Advanced proficiency in SQL and Python/PySpark for large-scale data analysis and automation.
Strong experience in machine learning techniques (supervised and unsupervised) for fraud detection and risk modelling.
Hands-on experience with Generative AI technologies including LLMs, prompt engineering, vector databases, and agentic frameworks (LangChain, LlamaIndex, AutoGen, etc.).
Experience working with big data platforms (e.g., Databricks) and building scalable data pipelines.
Strong understanding of rule engines, decision systems, and automated underwriting frameworks.
Experience in data visualization tools such as Power BI for fraud monitoring dashboards.
Key Competencies
Strategic thinking with strong analytical and problem-solving orientation.
Ability to balance fraud risk mitigation with customer experience and business growth.
Strong stakeholder management and executive communication skills.
Innovation mindset with a bias for experimentation and rapid deployment.
People leadership and mentoring capability.

Work arrangement
No