A machine learning approach to dengue forecasting: comparing LSTM, Random Forest and Lasso

• Autor(a) principal: Mussumeci, Elisa
• Data de Publicação: 2018
• Tipo de documento: Dissertação
• Idioma: eng
• Título da fonte: Repositório Institucional do FGV (FGV Repositório Digital)
• Texto Completo: http://hdl.handle.net/10438/24093
• topic: Machine learning; Neural networks; Time series; Forecasting; Epidemiology; Aprendizado por máquina; Redes neurais; Matemática; Análise de séries temporais; Redes neurais (Computação); Modelagem de dados; Análise de regressão; Dengue

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 a 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. As 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 all cities monitored by the Infodengue Project.