Manage risk analytics projects and ensure alignment with business goals. Ensure adherence to risk analytics policies and procedures. Provide strategic guidance on risk analytics practices. Lead a team of risk analysts. Build, Validate and Monitor Fraud Models.
Manage risk analytics projeBuild predictive models for real-time fraud detection systems.
- Evaluate and optimize existing ML models for performance, scalability, and explainability.
- Apply deep learning and advanced analytics for behavior analysis and risk profiling.
- Analyze transaction data to identify patterns, anomalies, and fraud trends.
- Perform exploratory data analysis (EDA) to understand customer behavior and potential fraud vulnerabilities.
- Translate data-driven insights into actionable recommendations for leadership and stakeholders.
- Collaborate with fraud strategy and operations teams to enhance fraud prevention frameworks.
- Validate and monitor predictive models for real-time fraud detection systems using valid monitoring metrics/KPI’s.
- Prepare technical documents related to fraud models and model validation. Validate the models using various techniques and KPIs, out of time validation etc.
- Set up monthly/quarterly and annual monitoring for the models using valid monitoring metrics/KPI’s.
- Perform Root Cause Analysis in case of deterioration of model performance/data issues.
- Evaluate and optimize existing ML models for performance, scalability, and explainability.
- Apply deep learning and advanced analytics for behavior analysis and risk profiling as part of
- Analyze transaction data to identify patterns, anomalies, and fraud trends.
- Perform exploratory data analysis (EDA) to understand customer behavior and potential fraud.
- Translate data-driven insights into actionable recommendations for leadership and stakeholders.
- Collaborate with other teams like fraud strategy to enhance fraud prevention frameworks.cts. Ensure adherence to policies. Provide strategic guidance. Lead a team.
- Hands on experience in Graph Knowledge Database / Graph Neural Networks based solutions.
- Handle the requests coming from client on Graph Knowledge Databases
- Provide solutions and mentor the team working with her/him on the graph solutioning
- 3-5+ years of experience in analytics preferably in Banking and Financial Services
- A minimum of 3 years of hands-on experience working on monitoring and validation of Machine Learning models to solve analytical use cases.
- Solid understanding of banking products, fraud types (e.g., account takeover, synthetic fraud, identity theft), and transaction systems.
- Knowledge of various statistical techniques used in analytics (regression, ML Models, Monitoring Metrics like KS, PSI, CSI, MAPE, Confusion Metrics etc.)
- Excellent problem-solving and analytical skills, with the ability to work on complex projects and deliver high-quality results.
- Proficiency in programming languages such as Python, and experience with ML related libraries.
- Experience with large-scale data processing and distributed computing frameworks is a plus.
- Strong communication skills, both written and verbal, with the ability to convey complex ideas to diverse stakeholders.
- At least 3 to 4 years of experience in Machine Learning and have hands on experience in Graph Knowledge Database / Graph Neural Networks based solutions.
- Hands-on experience in Python, and SQL. Good Knowledge on Classic ML algorithms.
- Working in any Fintech/Payments/Banking environment in fraud domain.
- Candidate should have worked priorly on at least one solution like AWS Neptune, Neo4J, Azure Cosmos Graph DB or any graph database.
- Experience in Snowpark/Pyspark is a plus.