*Result*: Evaluating risk in perishable-food manufacturing and logistics services from the view of human-AI synergy.

*There is no common consensus on human-AI synergistic risk evaluating framework among the extant studies, especially when simultaneously addressing the challenges caused by potential low-probability incident risks and highly sensitive quality-deterioration nature in perishable-food manufacturing and logistics services. We view AI-based technology as an effective incident-scenario forecasting tool when facing external environmental threats. We use a well-trained AdaBoost model to forecast the occurrence probability of each potential incident by observing and inputting real-time data about the nine key influencing factors. From the internal quality-deterioration perspective, we advocate human-expertise-dominated food-safety posterior information revision. In this specific framework, we therefore employ a hybrid approach by incorporating AdaBoost, cumulative prospect theory-based hesitant Pythagorean fuzzy set, and Graphic Evaluation and Review Technique to address the comprehensive risk-evaluating issues of scenario forecasting, response timing, and spatial ranking. The main findings reveal that our approach not only has advantages in mitigating the mixed ambiguity of internal quality deterioration and external environmental threats, but also has good performance and reliable robustness in a changing parameter environment. [ABSTRACT FROM AUTHOR]

Copyright of International Journal of Production Research is the property of Taylor & Francis Ltd and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)*

*Full text is not displayed to guests* *Login for full access*