Articles
Publication Date: 2025
Peer-to-Peer Networking and Applications (19366450)18(3)
Trustworthy manufacturer selection is essential for ensuring production quality control. Existing methodologies for selecting manufacturers often rely on participant sentiments or opinions, operating within a non-transparent framework. This paper proposes a comprehensive approach to trustworthy manufacturer selection by integrating a peer-to-peer system with a machine learning model. Specifically, it leverages blockchain technology to create a decentralized infrastructure that enhances transparency in the selection process. Furthermore, an intelligent model is introduced, incorporating a manufacturer evaluation module and the Bidirectional Encoder Representations from Transformers (BERT) language model to classify participant sentiments and opinions. To improve the efficiency of sentiment classification, under-sampling techniques are used to balance the datasets. The proposed method is applied within the pharmaceutical industry, where the increasing number of drug manufacturers has heightened the need for reliable manufacturer selection processes. The approach achieved a sentiment classification accuracy of 91% and an F1-score macro-average of 0.89. Comprehensive evaluations confirm the effectiveness of the proposed integrated model, offering a robust solution for trustworthy manufacturer selection. © The Author(s), under exclusive licence to Springer Science+Business Media, LLC, part of Springer Nature 2025.
Publication Date: 2025
Soft Computing (14327643)29(2)pp. 1243-1258
Demand forecasting has emerged as a crucial element in supply chain management. It is essential to identify anomalous data and continuously improve the forecasting model with new data. However, existing literature fails to comprehensively cover both aspects of anomaly detection and continuous improvement in demand forecasting. This study proposes an enhanced model to improve accuracy in the demand forecasting. The proposed model introduces a novel data handling method that incorporates an anomaly detection autoencoder, improved with anomaly correction mechanisms. The data handling approach simultaneously detects data anomalies, distinguishes between expected and unexpected anomalies, and corrects anomalous data, ensuring cleaner input for demand forecasting. Then, the proposed model employs a long short-term memory architecture for demand forecasting, enhanced with a continuous improvement method. Thus, the model not only forecasts demand but also retrains the model when the anomaly data surpasses the predetermined threshold, thereby improving the accuracy of forecasting. The results show that the proposed model outperforms other models in detecting data anomalies, achieving an average precision-recall of 0.922, a receiver operating characteristic value of 0.739, and a significance level of less than 0.05. Finally, the model exhibits superior performance in demand forecasting, with average mean squared error, root mean squared error, and mean absolute error values of 33.167, 4.347, and 1.509, respectively, all with a significance level of less than 0.05. © The Author(s), under exclusive licence to Springer-Verlag GmbH Germany, part of Springer Nature 2025.
