Performance Management in Business Organizations using Optimal and Attention-based Recurrent Neural Network for Enhancing the Productivity

The management by goals acts as a primary component of action for analyzing the performance of the organization’s demand of the employees in any bound of organization territory. The intelligence of the organization supports collecting significant data from a huge variety of unstructured data and changes them into useful data that enables the organizations to make illuminated policy decisions and enhance the organization’s productivity and efficiency. The complexities facing any enterprise in decision-making and business intelligence include risk-taking capability, resource failure, poor preparation, and plan failure. Deep learning has not attained much attention due to the efficacy has not been clearly examined in the decision-making within the organization. Hence in this proposed model, an efficient deep learning-aided system is developed for making decisions to improve production growth, where the data needed for the analysis is gathered from different business sectors. The collected data is applied to the Optimized and Attention Recurrent Neural Network (OAtt-RNN) for providing suggestions, which helps to boost up the productivity of the business. The decision-making efficiency of the proposed model is boosted by fine-tuning the attributes from OAtt-RNN using the Botox Optimization Algorithm (BOA). Effective business management generates a positive work environment and motivates employees to concentrate more on their work. The obtained outcome of the designed system is contrasted with other conventional models using different performance metrics to ensure the efficiency of our model.