Optimized Cloud Security: An AI-based Data Classification Approach for Financial Cloud Computing

Data categorization is the technique for classifying and arranging facts based on their value and sensitivity, in addition to offering suitable control and safety precautions. Data categorization is critical in cloud computing for finance because it helps to defend cloud-based monetary data. In this research, we aim to create an Artificial Intelligence (AI)-based totally Data type method for economic cloud computing. We proposed an innovative set of rules named Dynamic Vortex Search-driven Light Gradient Boosting Machine (DVS-LightGBM) for enhancing the method for classifying data in monetary cloud computing. The text cleaning process was conducted to preprocess the collected raw data, and it enhances the quality of the data acquired. We applied Latent Semantic Analysis (LSA) to extract the essential traits from the processed data. The dynamic vortex technique improves accuracy and increases convergence in the data classification process. The data classification procedure is based on cloud sensitivity levels. Our recommended approach consists of three classes, including standard, sensitive and highly sensitive. We implemented our suggested model in Python software. The result analysis phase is done on various parameters such as precision, accuracy, F1 score and recall. We conducted a comparison analysis with other existing methodologies to examine the effectiveness of the suggested model. The results of the trial demonstrate that the recommended strategy outperformed other existing methods in the data classification approach for financial cloud computing.