Summary
Overview
Work History
Education
Skills
Certification
Software
Languages
Websites
Interests
Accomplishments
Work Availability
Timeline
Generic
Eduardo de Abreu

Eduardo de Abreu

Senior Data Scientist | Data Science Specialist
Catanduva, Sao Paulo,SP

Summary

Senior Data Scientist with 8+ years of experience developing and deploying advanced analytics and machine learning solutions across financial services, healthcare, and agribusiness. Dual Master’s degrees in Computer Science (UFPEL) and Computer Engineering (FURG). Combines deep technical expertise (ML, Big Data, Cloud, Generative AI) with experience leading cross-functional teams and driving data strategy at scale. Passionate about solving complex business problems through data, driving operational efficiency, and mentoring high-performing teams.

Overview

12
12
years of professional experience
3
3
Certifications
3
3
Languages

Work History

Data Scientist

BanQi
09.2022 - Current
  • End-to-end ownership of credit risk, collection, and fraud models, ensuring their lifecycle from development to monitoring and retraining.
  • Built credit risk scoring models, fraud detection algorithms, and collection optimization systems in collaboration with Serasa, Boa Vista, Quod, ClearSale, and DataRisk.
  • Developed monitoring pipelines and dashboards for live model health tracking (AUC, KS, PSI, drift).
  • Improved approval rates while reducing default risk through advanced segmentation and challenger models.

Data Science Consultant

Arvo Saúde
02.2023 - 05.2023
  • Designed and deployed anomaly detection models and automated agents to detect fraud in medical claims.
  • Created data pipelines to process millions of claims with BigQuery and Python, delivering real-time fraud risk scores.
  • Aligned models with compliance rules and audit processes, reducing manual review workload by 60%.

Data Science Manager

Unimed Rio Preto
06.2021 - 09.2022
  • Built and led the organization’s data science division from the ground up, managing a cross-functional team of data engineers, scientists, and analysts.
  • Defined and executed the corporate data strategy, transforming siloed data sources into an integrated analytics platform supporting strategic decisions.
  • Designed and deployed machine learning models for risk stratification, healthcare utilization forecasting, and pricing optimization.
  • Identified patterns and behavioral trends from millions of medical records to personalize offerings and reduce operational costs.
  • Implemented Agile practices using Jira and Azure DevOps to plan sprints, track KPIs, and align technical delivery with business goals.
  • Reported directly to the executive board, translating complex analytical findings into business insights and strategic actions.

Data Scientist

Next
05.2021 - 06.2021
  • Implemented data quality metrics and monitoring routines using DAMA-DMBOK framework.
  • Automated continuous data quality checks and compliance reports, enabling proactive data governance.

Senior Model Validation Analyst / Data Scientist

Banco Bradesco
12.2018 - 05.2021
  • Senior Model Validation Analyst (Jul 2019 – May 2021): Validated models for Credit Risk (PD, LGD, PDD), AML, and Market Risk (VaR, FX Exposure) under strict regulatory standards.
  • Applied advanced performance monitoring (KS, AUC, PSI) and model governance practices.
  • Data Scientist – Loans & Financing Department (INOVA Talents Program): Selected for the bank’s innovation program to modernize the Loans & Financing area.
  • Developed customer clustering models and dynamic pricing models to optimize interest rates considering risk, competition, and profitability.
  • Built robust analytical datasets for scenario simulations and portfolio profitability analysis.

Developer and Data Analyst

Embrapa Pecuária Sul
02.2014 - 01.2015
  • Worked on the PampaPlus Net genetic breeding program from the Associação Brasileira de Hereford e Braford.
  • Used R and SAS to build algorithms that generated genetic merit scores to rank herds based on productivity, growth and carcass quality.
  • Integrated genetic, genealogical, and performance data pipelines, supporting traceability and data-driven herd improvement.

Education

M.Sc. - Computer Engineering

FURG
09.2019

M.Sc. - Computer Science

UFPEL
05.2017

B.Sc. - Information Systems

Universidade da Região da Campanha
01.2015

Skills

Languages & Modeling: Python, R, SQL, Java, C, SAS Logistic & Linear Regression, Random Forest, SVM, Gradient Boosting (XGBoost, LightGBM), Neural Networks, Clustering, NLP, Time Series

Certification

MIT xPRO — Data Science and Big Data (2021)

Software

Python

R

SAS

SQL

Spark

Jira/Azure DevOps/Linear

ML

AWS/CGP/AZURE/Databricks

Languages

Spanish
Elementary (A2)
English
Upper intermediate (B2)
Portuguese
Bilingual or Proficient (C2)

Interests

Artificial Intelligence & Machine Learning

Blockchain & Digital Assets Innovation

Applied Data Science in Healthcare & Finance

Credit Risk Optimization

Entrepreneurship & Startup Development

Strategy Games & Virtual Economy

Reading & Personal Development

Accomplishments

  • Developed and deployed credit risk models that improved default prediction accuracy by 15%.
  • Implemented anomaly detection on healthcare claims, reducing fraud-related costs by 12%.
  • Designed large-scale product deduplication pipelines (900k+ records) using embeddings and vector search.

Work Availability

monday
tuesday
wednesday
thursday
friday
saturday
sunday
morning
afternoon
evening
swipe to browse

Timeline

Data Science Consultant

Arvo Saúde
02.2023 - 05.2023

Data Scientist

BanQi
09.2022 - Current

Data Science Manager

Unimed Rio Preto
06.2021 - 09.2022

Data Scientist

Next
05.2021 - 06.2021

Senior Model Validation Analyst / Data Scientist

Banco Bradesco
12.2018 - 05.2021

Developer and Data Analyst

Embrapa Pecuária Sul
02.2014 - 01.2015

M.Sc. - Computer Science

UFPEL

B.Sc. - Information Systems

Universidade da Região da Campanha

M.Sc. - Computer Engineering

FURG
Eduardo de AbreuSenior Data Scientist | Data Science Specialist