Statistical Models for Predicting Chikungunya Incidences in India

Abstract

In Recent times, Chikungunya is considered as one of the most severe disease in India. It is caused by mosquitoes bite (CHIKV). But till now around the globe, scientists are unable to find the exact cure of this disease. Hence as a precautionary measure, there is an imperative need to predict the future possibilities of Chikungunya cases. Therefore, in this manuscript, machine learning based forecasting models are used for prediction of chikungunya cases in India for year 2018-2024. Analysis is conducted on the data of past years (2007-2017) Chikungunya cases in India. Box Cox, Mean Forecast, Seasonal Naive, and Neural Network are techniques are used for analysis and forecasting. The surpassing model is adopted based on the accuracy factor. Accuracy of the models are compared with respect to Root Mean Square Error and Auto Correlation Function. Result analysis reveal that the neural network model produces least error and hence is the best prediction model for our dataset in terms of accuracy.