Designing an Explainable AI-Based Decision Support Model for Evaluating Open Innovation in the Food Supply Chain

Document Type : Original Article

Authors

1 department of management, Ro.C., islamic azad university, Roudehen, iran

2 Department of Industrial Engineering, Sar.C. , Islamic Azad University, Sari, Iran,

3 department of industrial engineering, Par.C., islamic azad university, pardis, iran

4 department of industrial engineering, CT.C., islamic azad university, tehran, iran

10.22091/jemsc.2026.15967.1381

Abstract

This study aims to develop a data-driven and explainable framework for assessing the level of open innovation in the food supply chain. First, the evaluation indicators of open innovation were identified and finalized through a comprehensive literature review and expert opinions. Subsequently, the relative importance of the indicators was determined using the Fuzzy Best–Worst Method (FBWM). In the next stage, a machine learning model based on the CatBoost algorithm was developed to classify the level of open innovation into four different categories. To improve the interpretability of the proposed model, the SHAP method was employed for sensitivity analysis and to investigate the contribution of each indicator to the model outputs. The results demonstrated that the proposed model achieved a prediction accuracy of 95% and a Macro-F1 score of 0.946, indicating a highly satisfactory performance in predicting open innovation levels. The findings suggest that integrating multi-criteria decision-making methods, machine learning, and explainable artificial intelligence can provide an effective framework for supporting managerial decision-making in the field of open innovation.

Keywords

Main Subjects

Send comment about this article
CAPTCHA Image
Journal of Engineering Management and Soft Computing

Articles in Press, Accepted Manuscript
Available Online from 17 September 2026

Files

Share

How to cite

Statistics