Hello! I'm Francisco Iago

Sports Analytics: Multivariate Analysis

By Francisco Ferreira

This work was developed to obtain the degree of Bachelor in Statistics from the University of Brasília. My idea was to analyze the performance of players in the 2022 Brasileirão Série A (Brazilian League) using Multivariate Analysis techniques. The work was presented on Dec 18, 2023, the same day I formally obtained my bachelor's degree in statistics!

Ad A/B Testing

By Francisco Ferreira

A/B is a fundamental approach in statistical experimentation, often used to compare two versions of a product, marketing strategy, or whatever the variant of interest may be. In this context, I will apply an A/B analysis to the data found in this link. The aim will be to assess whether the responses between the control and exposed groups, using appropriate statistical tests to determine whether there is a significant difference in the proportions of 'yes' responses.

Judicial Efficiency Predictor (R Shiny)

By Francisco Ferreira

During my internship at the Regional Labor Court (10th Region), I developed an app in Shiny to simulate the placement of labor courts in the IGEST ranking. At the time, we used a dashboard made in Tableau, but it was barely functional. The biggest challenge was to create a dashboard that was fast, could filter values added by the user, and was able to show the ranking on a single page. The development process for this work can be found on my Github profile.

Which is the best forecast?

By Francisco Ferreira

During the Time Series course, one thing my professor used to say was that the best model is not always the one chosen by the software.

In this small study, I use one of the assignments I did during the course to try to demonstrate this point.

National Health Monitoring System

By Francisco Ferreira

Statistics Laboratory 2 was one of the last courses I took during my undergraduate studies. In it, my colleagues (Arthur Rodrigues, Ana Carolina Gomez, Daniel Miranda and Rayssa Lorrane) and I developed a dashboard using Looker. Until then, this was my first experience with this software. Initially, this represented a barrier, but with study and dedication, I managed to overcome these obstacles. The course syllabus, information about Previne, and the dashboard can be consulted below.

Big Data Processing with PySpark

By Francisco Ferreira

In a world where data analysis/data science is growing strongly, choosing the most appropriate tool is crucial for exploring the maximum amount of information. In this small study, I explore some possibilities of using the platform, utilizing the SQL language.