Revolutionizing AI-enabled Information Systems Using Integrated Big Data Analytics and Multi-modal Data Fusion

Transforming AI-based Information Systems (ISs) with synthesized Big Data Analytics and Multi-Modal Data Fusion highlights a big level forward in utilizing diverse data sources to enhance model effectiveness and decision-making. The integration of multi-modal data fusion, AI, and big data builds novel vision for optimizing ISs within multiple areas. In spite of the promise, recent research demonstrates critical drawbacks, encompassing poor combination of multi-modal data, inadequate controlling of big data volume and variation, and a lack of comprehensive taxonomies for categorizing AI-based ISs. These gaps highlight the need for a systematic technique for classifying and analyzing development in this field. In this research, we propose a taxonomy for AI-based ISs that utilizes synthesized big data analytics and multi-modal data fusion. We selected 36 state-of-the-art studies and classified them into six divisions: ERP Systems, CRM Systems, Supply Chain Management (SCM) Systems, Business Intelligence and Analytics Systems, Decision Support Systems (DSS), and Geographic ISs (GIS). We explored these publications in terms of their advantages, downsides, core ideas, simulation, and datasets. Our results represent that the majority of studies were published in 2024, 2023, and 2022, mainly by IEEE and Emerald, with publication rates of 23.5% and 20.6%, respectively. Accuracy and computational complexity indicated as the most significant evaluation parameters, captured 12.9% and 10.7% of articles, respectively. In addition, Python was indicated as the most prevalent programming language, implementing in 43.3% of the articles explored, highlighting its significance in advancing AI-based IS methods.