Book Release "Building a Platform for Data-Driven Pandemic Prediction: From Data Modeling to Visualization - The CovidLP Project"

October 8th | 2pm BRT
www.youtube.com/cacufmg

Opening:
- Prof. Mario Campos, Dean of Research at UFMG
- Prof. Glaura da Conceição Franco, DEST - ICEx/UFMG

Book Editors:
- Prof. Dani Gamerman, DEST - ICEx/UFMG
- Prof. Marcos O. Prates, DEST - ICEx/UFMG
- Prof. Thais Paiva, DEST - ICEx/UFMG
- Prof. Vinicius Mayrink, DEST - ICEx/UFMG

The work brings together the results obtained under the CovidLP Project, which provides daily, short- and long-term forecasts of confirmed cases and deaths of COVID-19. In addition to the book, the project also includes an application that provides information for general use and a package for more advanced users that makes it possible to analyze pandemic data.

The CovidLP Project was developed by undergraduate and graduate students and professors from the Department of Statistics (DEST) of the Exact Sciences Institute (ICEx) at UFMG.

Soon, the book "Building a Platform for Data-Driven Pandemic Prediction: From Data Modeling to Visualization - The CovidLP Project" will be released by the publisher Chapman & Hall/CRC, edited by DEST/UFMG professors Dani Gamerman, Marcos Prates, Vinícius Mayrink and Thaís Paiva, along with several collaborators, among them students of the graduate program in Statistics.

About the book:
- It is one of the results of the CovidLP project of short and long term predictions for COVID-19, which started to be developed at DEST in March 2020.
- It covers the construction of pandemic prediction platforms, providing an overview of probabilistic prediction for fully data-based modeling, and the use of tools such as R, Shiny and interactive plotting programs.
- Readers can follow different reading paths throughout the book, depending on their needs. Key audiences include applied statisticians, biostatisticians, computer scientists, epidemiologists, and practitioners interested in learning more about epidemic modeling in general, including the COVID-19 pandemic, and platform building.

Check out our website to stay updated on the book's release in September!

Due to a modification in the disclosure format of official data of Brazil and states by the Ministry of Health, we will have to suspend the predictions' updates temporarily until access to the complete data is normalized.

This modification also affected the exposure of the observed data series in the graphs of the first tab of our application, which for the time being is out of date. As soon as these problems are corrected, all graphs will be updated.

In the last months, our team has followed the trends of multiple waves in several of the countries analyzed, as well as the presence of weekly seasonality in the states of Brazil. These characteristics led to the implementation of different extensions of our model for each state and country on our list, which are actually the topics of the last posts here on this blog.

However, with the natural evolution of the complexity of the implemented models, many of these models have required more time to finish the analyzes. Recall that we currently provide daily predictions for a list of 46 countries, in addition to Brazil and its 27 states, with each region having two series (confirmed cases and deaths) adjusted separately. Even with all our efforts to optimize and parallelize the codes, it has not been uncommon to find several of these models needing more than 24 hours to finish.

With that, we inform that as of today, our forecasts will be updated only twice a week, on Mondays and Thursdays.