Data Scientist

About the roleWe are seeking a skilled and business-savvy Data Scientist with a focus on collections and servicing analytics to help optimize our customer recovery strategies and enhance operational effectiveness across the credit lifecycle. Working at the intersection of data, decisioning, and operations, you will leverage advanced analytics and machine learning to deliver actionable insights that improve customer outcomes, reduce losses, and enhance engagement. This role is ideal for someone with deep analytical expertise and a strong understanding of collections dynamics in a regulated financial services environment. Location: Pune, India.Main ResponsibilitiesCollections Strategy & Analytics Develop and deploy predictive models to optimize collections performance (e.g., contact strategy, cure likelihood, repayment propensity, roll rate prediction). Segment customers based on behavioural and financial data to tailor treatments and prioritization in early, mid, and late-stage collections. Support the design and analysis of test-and-learn experiments (e.g., communication channels, payment plans, incentive structures). Servicing Optimization Analyse servicing operations data to identify performance bottlenecks, inefficiencies, and improvement opportunities. Model and forecast call centre demand, digital servicing channel usage, and operational KPIs. Partner with operations teams to design data-driven interventions that improve customer experience and resolution rates. Modeling & Technical Delivery Use Python, SQL, and modern machine learning libraries (e.g., scikit-learn, XGBoost) to develop robust, scalable analytical solutions. Work with data engineers to implement models and decisioning logic into production environments (e.g., dialers, CRM systems, digital journeys). Create intuitive dashboards and reports for business users using BI tools (e.g., Power BI, Tableau). Governance & Compliance Ensure all modelling and data usage complies with regulatory standards (e.g., FCA, GDPR, Treating Customers Fairly). Document model performance, assumptions, and explainability in line with internal governance and audit standards. Required Qualifications: Bachelor's or Master’s degree in Data Science, Statistics, Mathematics, Economics, or a related discipline. 3+ years of experience in a data science or advanced analytics role, ideally within collections, recoveries, or servicing. Strong Python and SQL skills with practical experience building, validating, and deploying predictive models. Familiarity with the collections lifecycle and operational considerations (e.g., dialer strategies, queue management, digital outreach). Proven ability to partner with business stakeholders to design and deliver impactful analytics solutions. Strong analytical and communication skills, with the ability to translate complex analysis into actionable insight. Preferred Qualifications: Experience working in regulated credit environments (e.g., consumer lending, credit cards, auto finance, BNPL). Familiarity with collections platforms (e.g., Tallyman, CACS, FICO Debt Manager) and CRM systems. Knowledge of customer vulnerability assessment, affordability modelling, or agent-level performance analytics. Exposure to ethical AI, responsible ML, and explainability frameworks in a credit context. Pepper Advantage’s values and cultureOur mission is to help people succeed. Our clients, our customers, our employees. Our Values are ‘Can do’, ‘Balanced’ and ‘Real’.Pepper Advantage’s values support our vision, shape our culture and define how we interact with other employees and the attitudes we adopt towards our customers and clients. The values of Pepper Advantage support the organisation’s mission statement.Pepper Advantage’s unique outcome focused corporate culture aims to deliver fairness and value for clients and customers, consistently exceeding expectations in all measurable performance areas.Pepper Advantage is an equal opportunities employer.Role Profiles are subject to change in line with business needs.