Hossain, Md Shahadat and Ali, Mohammad and Haider, Parvin Sultana (2022) Generative AI and Predictive Business Analytics for Early Detection of Cybersecurity Threats in Enterprise Networks. American Journal of Economics and Business Management, 5 (12). ISSN 2576-5973

Text AJEBM_Generative+AI+and+Predictive+Business.pdf Download (592kB)

Abstract

Sophisticated attacks in the cyber world have made the need for intelligent solutions to enable earlier detection of cyber threats within enterprise networks more critical. The aim of this study is to explore the potential of Generative Artificial Intelligence (AI) and predictive business analytics in improving the enterprise's vulnerability management practices by conducting an exploratory analysis on an openly accessible cyber security vulnerabilities dataset. The research design was quantitative exploratory research design, secondary data were the vulnerability severity levels, attack vectors, exploitability scores, impact scores and vendor information. The data was preprocessed and visualized using R Studio where bar chart, pie chart, scatter plot and horizontal bar chart were used to find the pattern of vulnerabilities and relationships. The results show that the majority of the vulnerabilities are of Medium and High severity, network based attacks are the most common attack vector, there is a positive correlation between impact and exploitability, and there are a relatively higher number of vulnerabilities disclosed by several large software vendor companies. The study highlights that incorporating predictive business analytics with Generative AI can improve the interpretation of vulnerabilities, aid in making informed cybersecurity decisions and enable proactive risk prioritization. The results offer some practical guidance for enhancing enterprise cybersecurity readiness and early threat detection.

Item Type:	Article
Uncontrolled Keywords:	Cyber world, Cyber threat, Intelligent, Enterprise Network, Generative Artificial Intelligence, Exploratory, Data, Secondary Data
Subjects:	H Social Sciences
Depositing User:	admin eprints
Date Deposited:	18 Jul 2026 15:10
Last Modified:	18 Jul 2026 15:10
URI:	http://eprints.umsida.ac.id/id/eprint/16786

Actions (login required)

View Item