Roberto Rios

Build Python-based analytical data products for budgeting and credit-risk forecasting, translating business requirements into automated, decision-ready insights. • Define data validation rules, quality controls, naming conventions and monitoring standards to improve consistency, usability and auditability of shared data products.

• Analyzed large-scale operational datasets to identify process inefficiencies and improvement opportunities, generating over BRL 21M in cash gains. • Built an end-to-end analytics workflow covering data preparation, validation, model delivery and monitoring, generating BRL 27.24M in recovery value, BRL 380K in cost savings and a 7% gain in operational effectiveness. • Collaborated with data engineering teams to align analytical requirements with ingestion pipelines and platform capabilities.

Core coordinator responsible for handling, processing, and integrating large databases using SQL (Big Query/SAP Hana) and Python; Preparation of periodic analyses of results related to revenue protection, identifying lessons learned, opportunities, and performance deviations;

Developed and validated a Python predictive model for credit recovery, increasing effectiveness by 52% and reducing costs by 32%/ Engineered data pipelines and reporting for a national debt-relief program, enabling large-scale analysis and recovering approximately BRL 5.2M. / Scaled predictive modeling and KPI-driven prioritization workflows across multiple business units using SQL and Python, reducing costs by 60% and generating BRL 1.25M in savings.

Assisted in the collection, analysis, and interpretation of customer delinquency data, contributing to improved decision‑making in credit and recovery processes. Developed interactive dashboards to monitor and analyze collection performance, increasing visibility of key indicators and enabling faster tactical adjustments.

Automated selection and analysis of fraudulent/delinquent accounts using Python, cutting manual workload by 50% and contributing to BRL 12.5M in recovered debt.