Lead Analyst - Portfolio Intelligence & Fraud Analytics

About the role:

As a Portfolio Intelligence & Fraud Analytics Lead Analyst, you will play a critical role in helping Nium understand, monitor, and manage portfolio performance, fraud risk, payment abuse, and emerging customer behavior trends across its global payments ecosystem.

You will leverage data, analytics, and risk intelligence to identify opportunities, detect emerging risks, support fraud prevention initiatives, and provide actionable insights to business stakeholders. Working closely with Fraud, Risk, Compliance, Product, Operations, and Data teams, you will transform complex data into meaningful intelligence that supports business growth, effective risk management, and operational decision-making.

This role is ideal for a highly analytical professional who combines strong SQL and data analysis capabilities with an understanding of payments, fraud risk, portfolio monitoring, and customer behavior.

Key Responsibilities:

• Analyze customer, product, corridor, and market performance to identify emerging trends, risks, and growth opportunities.
• Develop and maintain portfolio monitoring dashboards and reporting frameworks and perform deep-dive analysis on customer segments, transaction behavior, payment flows, and portfolio concentration risks.
• Monitor key portfolio KPIs and KRIs, identifying significant changes and potential risk indicators.
• Conduct ad hoc analytical reviews to support business initiatives and strategic decision-making.
• Monitor fraud, chargeback, dispute, and payment abuse trends across products and geographies.
• Investigate fraud events to identify root causes, attack patterns, and control gaps.
• Support development and optimization of fraud rules, thresholds, and monitoring strategies.
• Assess fraud-control effectiveness and provide recommendations for improvement.
• Analyse customer friction metrics to balance fraud prevention objectives with customer experience.
• Support remediation activities for emerging fraud risks and elevated loss trends.
• Build and maintain dashboards using Looker, Power BI, Tableau, or similar analytics platforms.
• Develop and optimize SQL queries for fraud, portfolio, compliance, and operational reporting.
• Create recurring and ad hoc reports for Risk, Compliance, Product, and senior stakeholders.
• Develop data visualizations that communicate actionable insights effectively.
• Partner with Data Engineering teams to improve data quality, accessibility, and reporting capabilities.
• Monitor portfolio performance against internal risk thresholds and payment network requirements.
• Track fraud-to-sales ratios, chargeback ratios, dispute rates, approval rates, and transaction-risk indicators.
• Analyze emerging payment-risk trends and provide early warning indicators to stakeholders.
• Provide analytical support for fraud prevention, risk management, and portfolio optimization projects.

Requirements:

• 4-7 years of experience in Fraud Analytics, Portfolio Analytics, Payments Risk, Financial Crime Analytics, Business Intelligence, or Data Analytics.
• Strong analytical and problem-solving skills.
• Experience working with large datasets and identifying actionable insights.
• Advanced SQL skills and experience performing complex data analysis.
• Proficiency in Python for data analysis and automation.
• Experience building dashboards and visualizations using Looker, Power BI, Tableau, or similar tools.
• Understanding of payment ecosystems, fraud typologies, chargebacks, and transaction-risk indicators.
• Strong communication and stakeholder-management skills.
• Ability to present analytical findings to both technical and non-technical audiences.
• Preferred Qualifications
• Experience within fintech, payments, banking, card issuing, or acquiring environments.
• Knowledge of Visa and Mastercard fraud monitoring programs.
• Familiarity with AML, transaction monitoring, or financial crime controls.
• Experience with machine learning models or predictive analytics.
• Exposure to cloud data platforms such as Snowflake, Redshift, Databricks, or BigQuery.