AI-Enabled Big Data Visualization and Decision Support Using Responsive Web Technologies

Abstract

Decision-makers increasingly rely on dashboards to understand large and fast-changing datasets. Building effective dashboards, however, still depends on analysts choosing the right charts, spotting the important patterns, and designing layouts that work on every device. Artificial intelligence (AI) can take on much of this work. Visualization recommendation systems suggest suitable charts, automated insight discovery surfaces notable patterns, and natural-language interfaces let users ask questions in plain words, which large language models (LLMs) now translate into visualizations. This article proposes an architecture for AI-enabled big data visualization and decision support built on responsive web technologies. It combines seven layers: responsive presentation, AI visualization recommendation, automated insight discovery, natural-language interaction, metadata-driven configuration, workflow-driven decision execution, and autonomous operations. Using a design-oriented approach grounded in ten studies published between 2016 and 2025, the article presents the architecture, the flow from data to decision, and responsive design strategies. It also maps how the reviewed evidence is distributed across the architecture. It illustrates the architecture with a retail inventory decision support case used by regional managers on phones and analysts on desktops. It argues that AI makes visualization faster and more insightful only when its outputs are configurable, verifiable, and connected to governed decisions.