About Me

Passionate about data, storytelling, and elaboration hypothesis. Master of Sciences (MSc.) from the University of São Paulo in Medical Sciences program. Undergraduate in system analysis and development. Vast experience with multidimensional data, using SQL and NoSQL databases and developing interactive dashboards. Knowledge in Kibana, ElasticSearch, PowerBI, and other technologies to extract data insights. Researcher at Laboratory of Genetics and Molecular Cardiology at the Heart Institute (InCor) - University of São Paulo (USP) - Medical School, working with big data, data integration, data mining, and predictive algorithms. Use of artificial intelligence to improve risk prediction management of cardiovascular diseases through analysis and integration of molecular and genetic data with comprehensive clinical data. In partnership with Microsoft, I've developed a machine learning-based model to predict and reduce Public Schools’ dropouts. Scaled the predictive model to 5 thousand schools in São Paulo State, covering 3.5M students.

Main Stack

Some of the main technologies that I use and study
  • Big Data Analytics
  • Omics Analytics
  • Ontology Analytics
  • Financial Analytics
  • R
  • NodeJS
  • JavaScript
  • SQL/NoSQL
  • Python
  • Linux
  • Git
  • Docker

Experience

Some of my main professional experiences

B3 Brazlian Stock Exchange

Data Scientist Mar. 2022 - Present

  • Plan, develop, and apply leading-edge analytic and quantitative tools and modeling techniques to help B3 gain insights and improve decision-making. Review internal and external analytical techniques, processes, and tools - to improve efficiency and better B3 clients. Work closely with product sponsors to understand business needs and propose solutions.
  • Collaborate with Data Engineers and Software Developers to develop experiments and deploy solutions to production. Use domain knowledge and analytical expertise to suggest new product ideas.
  • Development of Python ML Models in AWS Environment
  • Build Alteryx flows to help business team to obtain insights from data
  • Create market indexes from different databases

Mar. 2022
  • Python
  • R
  • Spark
  • Machine Learning
  • Big Data
  • Alteryx
  • SQL Server
  • Agile Methodology

Heart Institute of São Paulo (University of São Paulo)

DataScientist/Bioinformatician Nov. 2018 - Present

  • Design and construction of new processes for data modeling, algorithms, predictive models, and custom analysis. Using regressions, neural-networks and bayesian models.
  • Large data integration using external APIs, web-scrapping and other data-mining techniques.

  • R
  • Python
  • Hadoop
  • NodeJS
  • MongoDB
  • Angular
Nov 2018

Cia de Processamento de Dados do Estado de SP - PRODESP

System Analyst/Data Scientist Feb. 2014 - Dec. 2021

  • In 2013, I was selected to work as a System Analyst at the São Paulo state education department. I’ve been promoted to Data Scientist in a project where I have implemented and validated predictive and prescriptive models, created and maintained statistical models, related to student’s life. It was a huge big data project using Azure cloud infrastructure in a partnership with Microsoft.

Feb. 2014
  • Java
  • WebServices
  • NodeJS
  • Machine Learning
  • Random Forests
  • Azure

Contact me

souzadevinicius@gmail.com