Machine learning for Covid-19: A review on forecasting models

Abstract

The accurate forecasting of Covid-19 cases remains a challenge even for comprehensive statistical models due to the complex dynamics inherent in largely urbanised populations. This difficulty, coupled with recent developments in artificial intelligence (AI), has led to a burgeoning interest in implementing machine learning (ML) algorithms to aid such predictions. Ever since the outbreak, various ML-based forecasting approaches have been trained and tested to support the design of intervention and healthcare strategies to protect the population. It is thus vital to assess the performance of these algorithms such that their accuracies, along with strengths and weaknesses, are known. This paper compares the forecasting performance of six commonly used ML models for Covid-19 forecasting. A brief analysis of the algorithms suitability for forecasting is also provided as part of the review. It is found that different algorithms were able to predict with varying degrees of accuracies in different scenarios, and that there is yet to be a definitive algorithm that is best for forecasting the Covid-19 outbreak.