Modeling Cloud Computing Risk Assessment Using Machine Learning

Cloud computing emerged in recent years as the most significant developments in modern computing. However, there are several risks involved in using a cloud environment. To make the decision of migrating to cloud services there is a great need to assess the various risks involved. The main target of risk assessment is to define appropriate controls for reducing or eliminating those risks. We conducted a survey and formulated different associated risk factors to simulate the data from the experiments. We applied different feature selection algorithms such as Best-First, and random search algorithms methods to reduce the attributes to 3, 4, and 9 attributes, which enabled us to achieve better accuracy. Further, seven function approximation algorithms, namely Isotonic Regression, Randomizable Filter Classifier, Kstar, Extra Tree, IBK, multilayered perceptron, and SMOreg were selected after experimenting with more than thirty different algorithms. The experimental results reveal that feature reduction and prediction algorithms is very efficient and can achieve high accuracy.