Predicting Non-Gaussian Data Distributions Using Artificial Intelligence and Machine Learning

Abstract

Healthcare sector is of prime importance post covid and the sector has actively initiated implementing AI-ML in data management and analysis. The data in case of healthcare sector is generally non-Gaussian in nature and the models are mostly accurate in case of Gaussian and not much is known in case of non-Gaussian. The objective of this paper is to help the health care sector to choose the better model in AI and Ml algorithm that suites better for all non- gaussian distribution. This study aims to analyse different AI and ML models and predict its accuracies and to the extent a model holds good for different type of non-gaussian data types. Different types of non-gaussian secondary and syntactic data will be used to study the models predictive capabilities. F1 score and confusion matrix will be used to check the model’s accuracy. With the help of different statistical tools this study aims to use different types of non-gaussian data that would be used for checking how they would perform which is very use full in business analytics back ground.