Ali, Mohammad and Hossain, Md Shahadat and Haider, Parvin Sultana (2024) AI-Driven Business Analytics Framework for Predicting and Mitigating Economic Risks in Small and Medium Enterprises (SMEs). American Journal of Technology Advancement, 1 (1). ISSN 2997-9382

Text AJTA_AI-Driven+Business+Analytics+Framework.pdf Download (567kB)

Abstract

In the realm of business analytics, AI stands out as a powerful tool for improving predictive economic risk management in Small and Medium Enterprises (SMEs). This research proposes an AI based business analytics model to predict and mitigate economic risks, combining financial literacy, financial constraints, technological innovation, CEO risk orientation, and organizational characteristics. A secondary data quantitative research methodology was taken from data published in 2021 available in Mendeley Data repository. Using R Studio, data preprocessing and exploratory data analysis were done to investigate the relationships between selected variables using a radar chart and correlation heatmap. Moreover, a Random Forest model was applied to determine the most influential predictors which affect the economic risk prediction. The results show that financial literacy contributes to the readiness of business analytics, and financial constraints, such as financing cost, guarantee requirements, debt maturity, and bank response, have a significant effect on the economic risk environment of SMEs. The AI based predictive model also finds firm size, firm age, leverage and return on assets as the most significant factors impacting on predictive performance. The results of these findings are used to propose an AI based business analytics framework that can help with evidence-based decision making and effective risk mitigation. The study's practical analytical framework can help SMEs enhance their financial sustainability, bolster organizational resilience, and make informed strategic decisions in a dynamic economic environment, highlighting its significance in the broader landscape of artificial intelligence in business analytics.

Item Type:	Article
Uncontrolled Keywords:	Business Analytics, AI, SMEs, Model, Economic Risks, Organizational, Data, Prediction, Predictive Model
Subjects:	H Social Sciences
Depositing User:	admin eprints
Date Deposited:	19 Aug 2026 06:51
Last Modified:	19 Aug 2026 06:51
URI:	http://eprints.umsida.ac.id/id/eprint/16993

Actions (login required)

View Item