Predicting the COVID-19 confirmed cases using K-means clustering algorithm - a case study for challenges in big data analytics

Several society and confidential region industries produce stores and investigate the big data with a purpose to progress the contributions they afford. This progression is referred as big data analytics. Biomedical studies generate a large amount of data that indirectly or directly influence public healthcare. This paper brings out numerous obstacles available in medical care based big data analytics, while much concentration is given to inaccuracy prevalent in the healthcare information that showcases the health of the patients as well as vital parameters of the common people. As a case study, dataset about COVID-19 confirmed patients and increase the life-saving chances. This model further tries to prove that a machine learning model's capability to handle the inaccuracies in the dataset and provide best possible outcome. Hence, this case study can lead other industries to utilise the inaccurate datasets to contribute progressively for humankind with the help of machine learning.