Intelligent Model for Predicting Intellectual Capital Maturity in Knowledge-Based Companies Using Machine Learning
نویسندگان
1 PhD Student, Department of Industrial Management, Faculty of Management and Economics, Science and Research Branch, Islamic Azad University, Tehran, Iran.
2 Associate Professor, Department of Industrial Engineering, North Tehran Branch, Islamic Azad University, Tehran, Iran.
3 Associate Professor, Department of Management, Malek Ashtar University of Technology, Tehran, Iran.
4 Associate Professor, Department of Industrial Engineering, Arak branch, Islamic Azad University, Arak, Iran
doi
10.22091/jemsc.2025.12548.1266چکیده
The aim of this research is to design an intelligent model for predicting the maturity of intellectual capital in knowledge-based companies located in industrial parks using machine learning algorithms. This study is applied-developmental in purpose and descriptive-modeling in methodology, utilizing a mixed approach for data collection. The data were gathered through a review of the literature, interviews with experts, and two questionnaires. For data analysis, various methods were employed, including the Delphi method, confirmatory factor analysis, and machine learning algorithms such as random forests, K-nearest neighbors, decision trees, naive Bayes, and multi-layer perceptron neural networks, using SPSS, PLS software, and various Python libraries. The results indicated that all models were capable of predicting the level of intellectual capital maturity; however, the multi-layer perceptron (MLP) model outperformed the others based on several criteria, including accuracy, precision, sensitivity, and F1 score, yielding the best results with values of 88.37%, 89.75%, 88.37%, 86.51%, and 0.918 in the area under the ROC curve.
