Abstract

Business organizations increasingly rely on the intelligent analysis of large-scale operational, financial, customer, and market datasets to improve strategic decision-making. The rapid growth of enterprise data creates new opportunities for analytical insights; however, the complexity, heterogeneity, and high dimensionality of business information present substantial challenges for conventional analytical approaches. Existing business analytics models often suffer from limited interpretability, suboptimal feature selection, and reduced adaptability when exposed to dynamic business environments. Such limitations affect the reliability of analytical outcomes and reduce stakeholder confidence in automated decision-support systems. To address these concerns, this study proposes an Explainable Genetic Analytics Optimization Network (EGAON), a novel hybrid framework that integrates the strengths of Genetic Algorithms with Explainable Artificial Intelligence (XAI) techniques for intelligent business analytics. The proposed EGAON method employs a genetic optimization mechanism for the identification of informative business attributes, while an explainability module provides transparent interpretations for predictive outcomes. The framework incorporates adaptive chromosome evolution, fitness-driven feature optimization, and explainable decision reasoning, which improves both analytical accuracy and model transparency. The architecture processes multidimensional business datasets through optimized feature extraction, evolutionary selection, predictive learning, and explanation generation stages. The proposed EGAON framework is evaluated using a business analytics dataset containing 25,000 records and 42 attributes. Experimental results demonstrate that the framework achieves 98.74% accuracy, 98.31% precision, 98.12% recall, and 98.21% F1-score, outperforming GA-ML, DNN-BA, and XAI-AF approaches. Furthermore, the framework reduces feature complexity by 41.56% and decreases computational requirements by 28.43% compared with existing methods. The obtained results confirm that the proposed framework provides accurate, efficient, and explainable business intelligence for strategic decision-making.

Authors

Maram Ashok¹, Abhijeet Das²
Malla Reddy College of Engineering, India¹, Indira Gandhi Institute of Technology, India²

Keywords

Business Analytics, Explainable Artificial Intelligence, Genetic Algorithm, Decision Support Systems, Feature Optimization