Senior Associate- Fraud Analytics

Hero FinCorp; Gurugram District; On-site; INR 1,500,000 - 2,100,000; Full time

Job summary

Hero FinCorp is seeking a Fraud Analytics professional to analyze end-to-end lending data, identify fraud patterns, and support risk- based decisioning. The role involves tracking FPD/EPD, performing root-cause analyses, and collaborating with FCU, Risk, and Business teams to balance fraud capture with customer experience.

Candidates should have 3–6 years in fraud analytics within BFSI/FinTech, strong SQL/Python skills, and experience with Power BI or similar tools.

Qualifications

• Bachelor's degree in engineering, Statistics, Mathematics, Economics, Computer Science, or related quantitative field (MBA / PGDM / Master’s in Analytics, Data Science, or AI is a plus).
• 3–6 years of experience in fraud analytics, risk analytics, or data science within BFSI / NBFC / FinTech lending.
• Experience working on consumer lending products and understanding of fraud risks across onboarding, underwriting, and repayment.
• Exposure to fraud detection techniques is preferred.
• Strong analytical experience in fraud/risk analytics for digital or retail lending portfolios.

Responsibilities

• Analyze end-to-end lending lifecycle data to identify fraud patterns and high-risk segments.
• Track key fraud indicators such as First Payment Default (FPD) and Early Payment Default (EPD).
• Perform deep-dive analyses on fraud spikes and portfolio deterioration to identify root causes.
• Support development and optimization of fraud rules, score cut-offs, and risk triggers.
• Build analytical datasets by combining internal and external data sources for fraud detection.

Skills

SQL

Python/PySpark

Data Visualization

Cloud Databricks

Generative AI basics

Education

Bachelor's degree in quantitative field

Tools

Power BI

Databricks

Job description

• Analyze end-to-end lending lifecycle data (application, onboarding, bureau, repayment, device) to identify fraud patterns and high-risk segments
• Track key fraud indicators such as First Payment Default (FPD), Early Payment Default (EPD), and abnormal delinquency trends
• Perform deep-dive analyses and root-cause investigations on fraud spikes, portfolio deterioration, and channel-level risks
• Support development, testing, and optimization of fraud rules, score cut-offs, and risk triggers to balance fraud capture and customer experience
• Build and maintain analytical datasets (feature marts) by combining internal and external data sources for fraud detection and monitoring
• Collaborate with Fraud Control Unit (FCU), Risk, Credit, and Business teams to provide data-backed insights and investigation inputs
• Develop and maintain fraud monitoring reports and dashboards using tools such as SQL, Python, and Power BI
• Assist in exploring new data sources (bureau, alternate data, device, telecom, etc.) and contribute to their evaluation for fraud use cases
• Support development of machine learning models and analytical frameworks for anomaly detection, behavioural segmentation, and fraud risk prediction
• Leverage basic Generative AI tools (LLMs, prompt-based workflows) for exploratory analysis, summarisation of fraud cases, and signal identification
• Participate in POCs and pilot programs to evaluate new fraud detection techniques, models, and data capabilities
• Translate identified fraud patterns (e.g., synthetic identities, mule accounts, sourcing fraud) into actionable analytical features and rules
• Present insights, findings, and recommendations to stakeholders in a clear and structured manner

Eligibility Criteria for the Job

Education

Bachelor’s degree in engineering, Statistics, Mathematics, Economics, Computer Science, or related quantitative field (MBA / PGDM / Master’s in Analytics, Data Science, or AI is a plus)

Work Experience

3–6 years of experience in fraud analytics, risk analytics, or data science within BFSI / NBFC / FinTech lending. Experience working on consumer lending products and understanding of fraud risks across onboarding, underwriting, and repayment. Exposure to fraud detection techniques is preferred.

Primary Skill

Strong analytical experience in fraud/risk analytics for digital or retail lending portfolios.

Ability to work with large datasets and derive actionable insights for fraud detection and

Technical Skills

• Strong SQL and Python/PySpark skills for data extraction, transformation, and analysis
• Basic to intermediate understanding of machine learning models (Logistic Regression, Tree-based models, clustering, anomaly detection)
• Exposure to data visualization tools such as Power BI or similar platforms
• Familiarity with cloud environments (e.g., Databricks) is preferred
• Basic understanding or exposure to Generative AI concepts such as LLMs, prompt engineering, or API-based usage is an added advantage

Soft Skills

• Strong problem-solving and analytical thinking capability
• Ability to work with ambiguity and convert problems into structured analysis
• Good communication and presentation skills
• Collaboration and stakeholder management skills across Risk, FCU, and Business teams
• Attention to detail and investigative mindset