Data-Driven Artificial Intelligence Models for Strategic Decision-Making in Engineering and Technology Management

Abstract

This paper will create a data-driven artificial intelligence system to improve strategic decision-making in the management of engineering and technology. A structured dataset that contains engineering project variables such as cost of the project, duration of time, risk index, and the use of resources was developed and analyzed using machine learning models, including Random Forest, Support Vector Machine (SVM), and Artificial Neural Network (ANN). Preprocessing data, feature selection, and k-fold cross-validation were used to guarantee the reliability and accuracy of the model. The results indicate that the Random Forest model performed best with an accuracy of 92.4%, as well as better precision, recall, F1-score, and AUC values. The analysis of the confusion matrix and the ROC curve was also a confirmation of its high classification ability. The risk index and resource utilization were the most significant variables found to influence the project outcomes by the feature importance analysis. The research notes that AI-based models are much more useful in improving prediction accuracy, minimizing uncertainty, and offering reliable decision support to engineering management applications.