An Increased Accuracy in Corona Crisis Prediction across Small Businesses Using Novel Centroid Tracking Algorithm Analysis of the K-Nearest Neighbors Algorithm

Abstract

Aim: The purpose of this research is to predict the Concussion of Corona Crisis over Small Businesses using Novel Centroid Tracking Algorithm Comparing K-Nearest Neighbors  Algorithm. Materials and Methods: NovelCentroid Tracking Algorithm with sample size = 110 and K-Nearest Neighbors with sample size =110 with G power (value =0.8) were evaluated many times to predict the efficiency percentage. Results: Novel Centroid Tracking algorithm has better efficiency (73.90%) when compared to K-Nearest Neighbors algorithm efficiency (64.70%). The results achieved with significance value p=0.815 (p>0.05) shows that two groups are statistically insignificant. Conclusion: Novel Centroid Tracking performed significantly better than the K-Nearest Neighbors algorithm.