A Machine learning approach to dengue forecasting - comparing LSTM, Random Forest and Lasso methods

Quem: 

Elisa Mussumeci

Onde: 

Praia de Botafogo, 190 - sala 537

Quando: 

19 de Abril de 2018 às 16h

We used the Infodengue database of incidence and weather time-series, to train predictive models for the weekly number of cases of dengue in 790 cities of Brazil. To overcome limitation in the length of time-series available to train the model, we proposed using the time series of epidemiologically similar cities as predictors for the incidence of each city. Machine Learning based forecasting models have been used in recent years with reasonable success. In this work we compare three machine learning models: Random Forest, Lasso and Long-short term memory neural network in their forecasting performance for cities monitored by the Infodengue Project.

*Texto informado pelo autor. 

Palestrante: 

Elisa Mussumeci é formada em Matemática Aplicada pela EMAp, mestre em Modelagem Matemática pela EMAp. Nesses seis anos como aluna da EMAP, participou de diversos projetos da escola como o MediaCloud, InfoZika e InfoDengue, adquirindo experiência nas áreas de big data, machine learning e análise de dados.