Securing tomorrow’s workforce: data analytics in workday cloud ecosystems

Abstract

The growing field of cloud-based enterprise management depends on data analytics in Workday cloud ecosystems since it makes workforce planning intelligent, flexible, and safe. However, as multidimensional workforce data becomes more sophisticated, it becomes increasingly difficult to guarantee the security, scalability, and quality of data throughout analysis and forecasting procedures. Using Geometry-BERT (GBERT), deep feature extractor and semantic representation, and whale-inspired ant swarm optimisation (WASO), which are optimal features selection, this paper proposes a security-conscious analysis model called GBERT–WASO-HH-DNN, the development of which is based on collecting and preprocessing synthetic human resources data in Kaggle, and subsequent feature embedding with the assistance of GBERT. The WASO algorithm, which is based on the behaviour of a group of whales and ants, enhances feature subsets by balancing between exploration and exploitation dynamics, which decreases by 32.7 the feature duplication in comparison to traditional particle swarm algorithms. The HH-DNN model does the classifications and predictions in the latent space, which enhances the stability and the rate of convergence. The findings indicate that the proposed model GBERT-WASO-HH-DNN has an accuracy of 96.82, a precision of 95.74, a recall of 96.23, and an F1 score of 96.05, which is better than the traditional models, including CNN-LSTM, Bi-GRU, and BERT-DNN in the accuracy. The suggested method also helps save the computational costs by 18.4% and enhances information security by 21.6% with the corresponding redundant encryption. This evidence demonstrates that the suggested solution does not only make the analysis in Workday cloud systems secure but also improves the intelligence and sustainability of the workforce.