Modelling Effective Parameters For Enhanced Interaction Practices In Industry: An AI Perspective

The focal point in digitalization and automation opportunities has been improving the industry's interaction practices for better productivity, customer engagement, and operational efficiency. This study, titled "Modelling Effective Parameters for Enhanced Interaction Practices in Industry: The paper titled "An AI Perspective", discusses how Interaction parameters by using machine learning methods RF and K-Means on Interaction coups and applying the COFI framework, namely Context, Content, Competency, and Culture. Applying the novel approach of data preprocessing, modelling and evaluation techniques for the utilization of the combination of supervised and unsupervised learning, this study established that the employed supervised models of learning offered an accuracy of 54% as found in the RF model, offering the highest efficient predictive accuracy and generalizable for industrial applications of general understanding. Nevertheless, K-Means clustering shows better results in the case of the COFI metric within the human-AI interaction analysis, regarding the Completeness (CC), the Correctness (CU), and the Accuracy (CA) measures, scoring more than 70%. These results show that even if RF is appropriate for decision-making for fine-tuned predictions, K-Means is better for segmenting targets based on the COFI framework to offer systematic data on interaction. So, this research adds to the limited body of literature on using AI for industrial interaction practices while arguing for integrating both RF and K-Means models to address the diverse needs of today's industries.