Predicting Malarial Outbreak using Machine Learning and Deep Learning Approach: A Review and Analysis

In the present era of information, data has revealed itself to be more valuable to organizations than ever before. By applying machine learning and deep learning approaches to historical or transactional data, we are now able to derive new ground breaking insights helping us to make better informed decisions and adopt the best strategies in order to face the events that are likely to happen in the future. In this paper, we have not only sought to establish a relationship between climatic factors and a possible malarial outbreak but we also tried to find out which algorithm is best suited for modeling the discovered relationship. For that purpose, historical meteorological data and records of malarial cases collected over six years have been combined and aggregated in order to be analyzed with various classification techniques such as KNN, Naive Bayes, and Extreme Gradient Boost among others. We were able to find out few algorithms which perform best in this particular use case after evaluating for each case, the accuracy, the recall score, the precision score, the Matthews correlation coefficient and the error rate. The results clearly implied that weather forecasts could be legitimately leveraged in the future to predict malarial outbreaks and possibly take the necessary preventing measures to avoid the loss of lives due to malaria.