Development of an Intelligent Security Risk Assessment Model in Cloud Computing Environments Using Supervised Machine Learning Algorithms

Abstract

Cloud computing has emerged as the key infrastructure for digital transformation, providing scalable and flexible access to computing resources, storage, and software services. Despite its major advantages such as scalability, flexibility, lower infrastructure costs, and on-demand access to computing resources, widespread adoption of cloud computing has introduced significant security concerns regarding the confidentiality, integrity, and availability of information. As a result, the development of intelligent approaches to assigning security risk has become an important requirement for cloud computing environments. The objective of this study is to develop an intelligent model for the assessment of security risk in cloud computing environments, using supervised machine learning algorithms. First, a systematic literature review was conducted to identify and classify the major factors affecting safety risk. The identified factors were evaluated and prepared for model development, resulting in a set of 18 safety risk factors. Three supervised machine learning algorithms—Decision Tree, K-Star (K*), and Random Filtered Classifier—were then evaluated and compared to predict the level of safety risk. To identify relevant variables and to support the model development, three methods for selecting features, namely Best First Search, Ranker, and Random Search, were applied using the WEKA and Orange Data Mining environments. The performance of the model was evaluated using the Root Mean Square Error (RMSE) and correlation coefficient (R) under different training–testing data-split scenarios. The results showed that the 95% training and 5% testing split produced the lowest RMSE among the evaluated data-split scenarios. The Decision Tree algorithm achieved the lowest RMSE across the evaluated scenarios, reaching 0.0018 under the 95% training and 5% testing split. The Random Filtered Classifier and K-Star algorithms produced identical RMSE values across the evaluated scenarios. These findings demonstrate the applicability of supervised machine learning algorithms to intelligent security risk assessment and provide a basis for developing data-driven approaches to security risk analysis in cloud computing environments.