Artificial Intelligence–Driven Strategic Decision Frameworks for Engineering and Technology Enterprises
TL;DR
The findings indicate that the model will have a high predictive accuracy and reliability, with ANOVA showing statistically significant differences among models (p < 0.05), and the results of cross-validation confirm the stability and generalizability of the model to various data subsets.
Abstract
The concept of Artificial Intelligence (AI) is rapidly changing the way strategic decision-making processes in engineering and technology-driven enterprises are conducted, by facilitating data-driven insights and predictive analysis. This paper suggests an artificial intelligence-based strategic decision model with the Random Forest model, which is supported by statistical validation methods, such as ANOVA, correlation analysis, regression analysis, cross-validation, and feature importance analysis. The findings indicate that the model will have a high predictive accuracy and reliability, with ANOVA showing statistically significant differences among models (p < 0.05). Both correlation and regression results show that the risk level and technological uncertainty have a negative effect on the results of decision making, and team experience has the most significant positive impact. The results of cross-validation also confirm the stability and generalizability of the model to various data subsets. The feature importance analysis identifies the most important variables that determine the strategic decisions. The suggested framework will improve the quality of decisions made, facilitate risk management, and enhance resource allocation. The current study is an addition to AI-based decision systems that incorporates predictive modeling in conjunction with statistical validation of enterprise applications.