Leveraging AI for fine-grained food safety risk forecasting in sparse data conditions
2026-08-03 • Artificial Intelligence
Artificial Intelligence
AI summaryⓘ
The authors created a smart computer method that uses lots of past food inspection data combined with information about cities to predict where food safety problems might happen. They designed a special way to train their model that helps it learn well even when there isn’t much local data. Their tests show this method predicts risks better than older methods. They also worked with a government group to try it out in real inspections, which helped find food safety issues more effectively. The study suggests this technology could help inspectors target their work earlier and more precisely to keep food safer.
Transformer modelWilson intervalsemi-supervised learningfood safetyrisk forecastinginspection dataStatistical Yearbookdeep learningdecision supportpublic health
Authors
Dongqi Wang, Weiwei Chen, Han Zhou, Weihua Zhou
Abstract
Ensuring food safety represents a critical public health challenge, particularly when inspection resources are limited and regional sampling data are sparse. This study proposes a Transformer-based framework capable of forecasting fine-grained, city-level food safety risks by unifying over 11 million inspection records with supplemental demographic, economic, and environmental indicators extracted from the Statistical Yearbook. A three-stage pretraining design leverages partial supervision from the Wilson interval (capturing both safety and risk rankings), together with semi-supervised label refinement, to effectively utilize historical records even when local sample sizes are insufficient. Experimental evaluations on data from 2022 show that the proposed approach outperforms baselines significantly. A subsequent field experiment in collaboration with the Zhejiang Provincial Administration for Market Regulation further demonstrates improved detection rates and more efficient allocation of inspection resources compared to a manually developed plan. Observations of regulatory decision-making reveal a threshold-based heuristic employed by inspectors, hinting that additional training or decision-support interfaces could further enhance the impact of AI-generated risk scores. Overall, these findings underscore that a rigorous integration of large-scale public inspection data, Wilson interval-based confidence modeling, and advanced deep learning can facilitate earlier and more granular identification of food safety threats. By reducing reliance on reactive measures alone, the proposed framework has the potential to advance proactive, data-driven oversight of the global food supply.