Machine-learning forecasting for Dengue epidemics - Comparing LSTM, Random Forest and Lasso regression

Effective management of seasonal diseases such as dengue fever depends on timely deployment of control measures prior to the high transmission season. As the epidemic season fluctuates from year to year, the availability of accurate forecasts of incidence can be decisive in attaining control of such diseases. Obtaining such forecasts from classical time series models has proven a difficult task. Here we propose and compare machine learning models incorporating feature selection,such as LASSO and Random Forest regression with LSTM a deep recurrent neural network, to forecast weekly dengue incidence in 790 cities in Brazil. We use multivariate time-series as predictors and also utilize time series from similar cities to capture the spatial component of disease transmission. Among the compared models, the LSTM recurrent neural network model displayed the smallest predictive errors in predicting incidence of dengue out of sample, in cities of different sizes.