Analyst - Collections Analytics

About bluCognition

bluCognition is an AI-powered commercial credit intelligence company serving lenders and financial institutions. Our platform combines commercial credit data contributed by 150+ lenders with AI-driven analytics, banking data and fraud detection to help our clients make faster, better credit decisions. Our product suite includes bluSense, which converts bank statements into standardized, categorized transaction data with real-time financial insights, and FraudLens, which detects document tampering and first-party fraud. Alongside our data products, we run a managed services business supporting underwriting, fraud review, and KYC/KYB and sanctions screening operations for our clients, with teams across North America, Asia and Europe.

About Role

Collections Specialist will play a key role in optimizing collections strategies across the telecom debt lifecycle by analyzing existing collections populations to uncover behavioral patterns, segment-level trends, and strategic gaps. This role will leverage risk analysis to build, monitor, and continuously improve existing collections strategies that drive smarter prioritization and treatment of delinquent accounts. The ideal candidate combines strong technical skills in SQL, Python/R, and MS Excel with a solid understanding of collections and credit risk concepts to deliver smart strategies and actionable insights.

Key Responsibilities:

• Conduct analysis of end-to-end collections activities: outreach (email, phone, portal messages), negotiation of payment arrangements, settlement discussions, chargeback resolution, and escalation when necessary.
• Conduct risk analysis to assess portfolio exposure, borrower/subscriber risk profiles, and the effectiveness of collections interventions across different customer segments.
• Apply machine learning techniques and engineer new features to build and refine predictive models that improve risk segmentation, prioritization, and treatment strategies for delinquent accounts.
• Monitor, evaluate, and continuously improve existing collections models, tracking performance metrics and recalibrating as needed to maintain accuracy and business relevance.
• Design and deliver ongoing reporting and dashboards that translate model outputs and collections performance into actionable insights for stakeholders.
• Partner closely with payments, recoveries, and analytics teams, as well as senior leadership, to conduct ad-hoc analyses, answer strategic questions, and drive data informed decision-making across the collections function.
• Investigate disputed card transactions, First Party and Third-Party chargebacks, suspected fraud or ATO issues, and coordinate with Fraud/Credit Abuse teams.
• Execute skip-tracing, business entity and cardholder verification, and research into corporate ownership and contact information using internal systems, public records and third-party applications.
• Report Collections KPIs and SLAs (cure rate, recovery rate, promise-to-pay rate, right-party contact rate) and contribute to process improvements.

Required Skills & Qualifications

• Bachelor’s degree in computer science, Statistics, Finance, or related field preferred.
• 3-5+ years of experience in data science or analytics, ideally within collections, credit risk, telecom, or financial services.
• Strong proficiency in SQL and a programming language such as Python or R for data manipulation, statistical analysis, and model development.
• Hands-on experience with machine learning techniques (e.g., logistic regression, decision trees, gradient boosting, clustering) and feature engineering for predictive modeling.
• Solid grounding in statistics and risk analysis, including model validation, performance monitoring (e.g., KS, AUC, PSI), and score/model recalibration.
• Experience working with large, complex datasets, including data cleaning, wrangling, and pipeline development.
• Proficiency in MS Excel, including pivot tables and complex formulas to deliver clear, actionable reports for senior stakeholders and operations teams.

Preferred Attributes

• Experience with collections or credit risk strategy concepts, such as delinquency buckets, roll rates, propensity-to-pay models, and treatment/segmentation strategies.
• Knowledge of uplift modelling, A/B testing, data visualization tools (like Power BI, Tableau) is a plus. Certifications in collections, credit management, or card operations compliance are a plus.