Open Access

ARTICLE

A Hierarchical Attention Framework for Business Information Systems: Theoretical Foundation and Proof-of-Concept Implementation

Sabina-Cristiana Necula^*, Napoleon-Alexandru Sireteanu

Department of Accounting, Business Informatics and Statistics, Faculty of Economics and Business Administration, Alexandru Ioan Cuza University of Iasi, Iasi, 700505, Romania

* Corresponding Author: Sabina-Cristiana Necula. Email:

Computers, Materials & Continua 2026, 86(2), 1-34. https://doi.org/10.32604/cmc.2025.070861

Received 25 July 2025; Accepted 21 October 2025; Issue published 09 December 2025

Abstract

Modern business information systems face significant challenges in managing heterogeneous data sources, integrating disparate systems, and providing real-time decision support in complex enterprise environments. Contemporary enterprises typically operate 200+ interconnected systems, with research indicating that 52% of organizations manage three or more enterprise content management systems, creating information silos that reduce operational efficiency by up to 35%. While attention mechanisms have demonstrated remarkable success in natural language processing and computer vision, their systematic application to business information systems remains largely unexplored. This paper presents the theoretical foundation for a Hierarchical Attention-Based Business Information System (HABIS) framework that applies multi-level attention mechanisms to enterprise environments. We provide a comprehensive mathematical formulation of the framework, analyze its computational complexity, and present a proof-of-concept implementation with simulation-based validation that demonstrates a 42% reduction in cross-system query latency compared to legacy ERP modules and 70% improvement in prediction accuracy over baseline methods. The theoretical framework introduces four hierarchical attention levels: system-level attention for dynamic weighting of business systems, process-level attention for business process prioritization, data-level attention for critical information selection, and temporal attention for time-sensitive pattern recognition. Our complexity analysis demonstrates that the framework achieves O(n log n) computational complexity for attention computation, making it scalable to large enterprise environments including retail supply chains with 200+ system-scale deployments. The proof-of-concept implementation validates the theoretical framework’s feasibility with MSE loss of 0.439 and response times of 0.000120 s per query, demonstrating its potential for addressing key challenges in business information systems. This work establishes a foundation for future empirical research and practical implementation of attention-driven enterprise systems.

---

Keywords

---