This study conducts a comparative analysis of various machine learning and deep learning models for predicting order quantities in supply chain tiers. The models employed include XGBoost, Random Forest, CNN-BiLSTM, Linear Regression, Support Vector Regression (SVR), K-Nearest Neighbors (KNN), Multi-Layer Perceptron (MLP), Recurrent Neural Network (RNN), Bidirectional LSTM (BiLSTM), Bidirectional GRU (BiGRU), Conv1D-BiLSTM, Attention-LSTM, Transformer, and LSTM-CNN hybrid models. Experimental results show that the XGBoost, Random Forest, CNN-BiLSTM, and MLP models exhibit superior predictive performance. In particular, the XGBoost model demonstrates the best results across all performance metrics, attributed to its effective learning of complex data patterns and variable interactions. Although the KNN model also shows perfect predictions with zero error values, this indicates a need for further review of data processing procedures or model validation methods. Conversely, the BiLSTM, BiGRU, and Transformer models exhibit relatively lower performance. Models with moderate performance include Linear Regression, RNN, Conv1D-BiLSTM, Attention-LSTM, and the LSTM-CNN hybrid model, all displaying relatively higher errors and lower coefficients of determination (R²). As a result, tree-based models (XGBoost, Random Forest) and certain deep learning models like CNN-BiLSTM are found to be effective for predicting order quantities in supply chain tiers. In contrast, RNN-based models (BiLSTM, BiGRU) and the Transformer show relatively lower predictive power. Based on these results, we suggest that tree-based models and CNN-based deep learning models should be prioritized when selecting predictive models in practical applications.

This study aims to examine how marketing mix and trust theories influence users’ intentions to adopt herbal platform services in Thailand and examine the impact of these intentions on actual service usage, placing a special focus on the integration of technologies in the context. The significant potential for growth in Thailand’s herbal business and the currently underutilized online platforms, it is crucial for stakeholders to understand the determinants of investment intentions. Merging marketing mix and trust theories, this research offers a comprehensive analysis of factors influencing the use of herbal platform, highlighting the relevance of herbal in enhancing service adoption. This study utilized a quantitative approach, gathering data through online surveys from 416 users of online herbal platforms in Thailand using SEM to examine the impact of gender on consumers’ decisions to use these platforms. This study provides insights into effective business strategies for herbal companies and contributes novel perspectives to the literature on herbal services. It specifically examines cognitive and emotional trust impacts and explores gender dynamics within the context of Health development. The study clarifies the roles of these factors and assesses the impact of gender on platform adoption, highlighting the importance of m-Health services in facilitating this process. Enhancing user engagement with herbal platform services requires prioritizing influential determinants, streamlining the investment experience, and underscoring the sector’s contribution to economic revitalization. Authorities should prioritize simplifying the investment landscape and initiating advocacy campaigns, while platform developers are advised to improve the user experience, bolster educational efforts, and heighten awareness of the investment advantages within the herbal industry. This research provides stakeholders with insights into the factors that enhance Thais’ engagement with herbal market platforms, especially via online channels. Identifying these key drivers is anticipated to boost participation in the herbal market, thereby contributing positively to Thailand’s economy.

The paper analyzes the corporate carbon emissions and GDP contributions of the top ten companies by turnover for 2020–2023 in Germany, South Korea, China and the United Kingdom. Focusing on Scope 1, 2, and 3, the study explores the contribution of these companies to carbon intensity across different sectors and economies. The analysis shows that there are significant gaps in carbon efficiency, with the UK’s and Germany’s firms emitting the lowest emissions per unit of GDP contribution, followed by China and South Korea. Additionally, the study further examines the impact of Economic Policy Uncertainty on both firm carbon intensity and economic productivity. While EPU is positively associated with GDP contributions, its impact on emissions is nuanced. Firms apparently respond to policy uncertainty by increasing energy efficiency in direct (Scope 1) and energy-related (Scope 2) emissions but find it more difficult to manage supply chain emissions (Scope 3) in that case. The results point out the critical role of comprehensive ESG reporting frameworks in enhancing transparency and addressing Scope 3 emissions, which remain the largest and most volatile component of corporate carbon footprints. The paper then emphasizes the importance of standardized ESG reporting and bespoke policy intervention for promoting sustainability, especially in carbon-intensive industries. This research contributes to the understanding of how industrial and policy frameworks affect carbon efficiency and economic growth in different national contexts.