Speaker: Nooriyan Poonawala-Lohani, PhD student, supervised by Mehnaz Adnan, Pat Riddle, and Joerg Wicker

Abstract: Influenza is a communicable respiratory illness that can cause serious public health hazards. Due to its huge threat to the community, accurate forecasting of Influenza-like-illness (ILI) can diminish the impact of an influenza season by enabling early public health interventions. Current forecasting models are limited in their performance, particularly when using a longer forecasting window. To be able to extend the forecasting window without a substantial decrease in performance, we propose  to  use  additional  features  such  as  weather  data.  Commonly  used methods to forecast ILI, including statistical methods such as ARIMA, limit  prediction  performance  when  using  additional  data  sources  that might have complex non-linear associations with ILI incidence. We propose a  novel  time  series  forecasting  method,  Randomized  Ensembles of Auto-regression chains (Reach). Reach implements random chain  ensembles  for  multi-step  time  series  forecasting  using  machine learning models. We evaluate this new approach on ILI case counts in Auckland, New Zealand from the years 2015-2018 and compare its performance with other standard methods. The results demonstrate that the proposed method performed better than baseline methods when applied to this multi-variate time series forecasting problem.