Advancing business intelligence systems for organizational decision making and effective management

Business intelligence (BI) systems enable organizations to examine data for well-informed decision-making, boosting efficiency, management, and business performance. Despite the current BI systems, they experience some shortcomings, such as poor data integration, non-existence of real-time analytics, limited user accessibility, and inability to support changing business environments. Overcoming such challenges is instrumental in improving business processes and refining decision-making functions. Research focuses on the development of BI systems by introducing more sophisticated tools for enhanced data consolidation, real-time analysis, and better decision-making. The approach considered in this work is the Intelligent Flower Pollinator-mutated Enriched GRU (IFP-EGRU) model that aims to enhance the accuracy of time-series prediction, especially in predicting sales and strategic business decision-making. The data set includes time-series data on sales, customer activity, market trends, inventory, financial transactions, and demand forecasting. Pre-processing involves handling missing values using imputation methods and applying normalization to scale the features. Linear Discriminant Analysis (LDA) is utilized to learn meaningful features by maximizing class separability and hence improving classification performance. The IFP algorithm optimizes parameter selection and solution space exploration to minimize the model, and the Enriched GRU (EGRU) enhances the architecture of GRU with massive improvements in forecasting accuracy. Experimental results confirm that IFP-EGRU obtains a forecasting accuracy of 97%, recall of 96.2%, F1-score of 95.9%, and precision of 95.3%. These gains significantly improve prediction ability in time-series prediction, resulting in more accurate business insights and strategic decision-making. The suggested enhancements enhance BI systems to be more responsive and efficient in processing intricate business cases.