Rodrigo Falcão

I am a Data Scientist with over 5 years of experience delivering end-to-end analytical solutions, primarily within the financial (payments and pensions) and retail sectors. My expertise lies in bridging the gap between advanced Statistical Modeling, Machine Learning, and Cloud Engineering to transform complex datasets into scalable business assets. I am currently deepening my academic foundation through a Master’s Degree in Statistics at the Federal University of Pernambuco, complementing my MBA in Data Science and Bachelor's in Computer Science.

Throughout my career, I have driven measurable impact through automation, predictive modeling, and optimization:

• Generative AI & NLP: Leveraged Amazon Bedrock (LLMs) to automate actionable report generation for cross-functional teams and built an end-to-end PDF extraction pipeline using Python, AWS ECS, and ECR.

• Predictive Modeling: Developed a time-series machine learning engine to identify customer churn, significantly accelerating retention actions. I have strong experience building and deploying models using frameworks like TensorFlow, PyTorch, and Scikit-Learn.

• Advanced Optimization: Designed and implemented linear stochastic programming and convex optimization models for asset and liability management, successfully reducing pension contribution rates by an average of 5%.

• Big Data & Performance: Spearheaded product performance optimization that slashed runtime by more than 24 hours. Additionally, I automated a manual financial reconciliation process, resulting in a 90% reduction in processing time.

• Graph Data Science: Modeled complex networks using NetworkX and Gremlin on AWS Neptune, generating a graph-based recommendation engine that provided faster, more accurate insights for decision-makers.

Technical Toolkit:

• Programming: Python (Pandas, Polars, Numpy), R, SQL, and GAMS.

• Machine Learning: TensorFlow, PyTorch, Scikit-Learn, Amazon Bedrock, aeon, and imbalanced-learn.

• Cloud & MLOps: AWS (SageMaker, Glue, Athena, Lambda), Azure, Databricks, PySpark, Apache Airflow, Docker, and Git.