EL V.2 Model for Predicting Food Safety Risks at Taiwan Border Using the Voting-Based Ensemble Method

Abstract

Border management serves as a crucial control checkpoint for governments to regulate the quality and safety of imported food. In 2020, the first-generation ensemble learning prediction model (EL V.1) was introduced to Taiwan’s border food management. This model primarily assesses the risk of imported food by combining five algorithms to determine whether quality sampling should be performed on imported food at the border. In this study, a second-generation ensemble learning prediction model (EL V.2) was developed based on seven algorithms to enhance the “detection rate of unqualified cases” and improve the robustness of the model. In this study, Elastic Net was used to select the characteristic risk factors. Two algorithms were used to construct the new model: The Bagging-Gradient Boosting Machine and Bagging-Elastic Net. In addition, Fβ was used to flexibly control the sampling rate, improving the predictive performance and robustness of the model. The chi-square test was employed to compare the efficacy of “pre-launch (2019) random sampling inspection” and “post-launch (2020–2022) model prediction sampling inspection”. For cases recommended for inspection by the ensemble learning model and subsequently inspected, the unqualified rates were 5.10%, 6.36%, and 4.39% in 2020, 2021, and 2022, respectively, which were significantly higher (p < 0.001) compared with the random sampling rate of 2.09% in 2019. The prediction indices established by the confusion matrix were used to further evaluate the prediction effects of EL V.1 and EL V.2, and the EL V.2 model exhibited superior predictive performance compared with EL V.1, and both models outperformed random sampling.

Application and effectiveness of artificial intelligence for the border management of imported frozen fish in Taiwan

“…The purpose of implementing an integration strategy is to combine multiple different classifiers for improving the classification accuracy of the overall classification system. To improve and stabilize the model’s predictive performance, a second-generation ensemble learning prediction model was developed based on seven algorithms to enhance the “detection rate of unqualified batches” [ 2 ]. Since 2020, the BPI system has been adopted in phases for different categories of products to perform risk management, and the risk verification intervention points refer to the risk management steps shown in Fig.…”

“…Furthermore, the data change over time; thus, the model’s ability to obtain accurate predictions may decrease. According to historical border inspection application data, the number of noncompliance batches accounts for a small proportion of the total number of inspection applications, and modeling based on these data can easily result in prediction bias [ 2 ].…”

“…To effectively use the large amount of data accumulated from annual border inspections, the TFDA consulted the data sources and practices followed by the EU and US. After identifying and assessing the risk factors, TFDA developed the Border Prediction Intelligent (BPI) system [ 2 ] ( Fig. 2 ).…”