Litcius/Paper detail

Time Series Analysis of the Covid-19 Datasets

Sujeet Maurya, Shikha Singh

20202020 IEEE International Conference for Innovation in Technology (INOCON)16 citationsDOI

Abstract

This research is focused on the data analytics for the available data for COVID-19 pandemic disease. In this research work, Python and its libraries are applied for the exploratory data analysis of this secondary dataset. Considering the variation of the scenario with time, it has been observed to analyze the data with the time series analysis in order to forecast the future effect of Coronavirus globally or individually. This analysis has been conducted using seven forecast methods. But only the four methods with the least errors are reported here, viz. NAIVE, Holt's linear trend method, Holt's Winter seasonal method, and ARIMA. It is so much required to forecast the future possibilities in such random and unique occurrence of the pandemic around the world. This analysis helps many researchers and scientists to understand the statistical forecasting which will be a great support for future preparedness. This analysis will be helpful for the organizational and social entities to tackle this pandemic across the country.

Topics & Concepts

Time seriesAutoregressive integrated moving averageData scienceComputer sciencePandemicCoronavirus disease 2019 (COVID-19)Exploratory data analysisPreparednessData analysisAnalyticsExploratory analysisData miningEconometricsOperations researchMachine learningInfectious disease (medical specialty)MathematicsPolitical scienceMedicineDiseaseLawPathologyCOVID-19 epidemiological studiesCOVID-19 Pandemic ImpactsCOVID-19 diagnosis using AI