Experience

Developed solutions to automate reports and key metrics through Shiny web dashboards, R scripts and Dropbox
Designed, maintained and managed data pipelines using Amazon Redshift, R and Jenkins
End-to-end planning and management of data science projects towards timely and desired outcomes

Optimization Team / Exchange Team

Developed and built algorithms on floor recommendations that increased Publisher’s revenue by 20%
Worked closely with software engineers to create an automated process and an experimentation framework.
The only Data Scientist in the company
Design and develop click prediction models and algorithms.
Developed price floor recommendations.
Worked with 100GB+/day using tools such as Spark and H2O.
Built data science pipeline using Spark (PySpark) - from raw logs to data ready to model.
Built framework, design, and analysis of experiments.

Lead a team of 5 Data Scientist
Worked on pre and post-sales engagements with several clients including Finance, Healthcare, Advertising, etc.
Created the appropriate analytics workflows that best deliver relevant insights and predictive models for a client applying techniques such as machine learning and statistical analysis to deliver business value.
Write documentation and Knowledge Repo
Train customer teams on best practices for data analysis/modelling within Alpine’s software

Course: Information Design (Instructor: Pino Trogu)

Taught designers on how to pre-process and visualize data with R for sketching and development, and Illustrator for cleaning up and finalizing the visualization (Textbook: “Visualize This” by Nathan Yau)

Projects:

Bands: Liquidificalouca 📹 & Paula Leal