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.

By reviewing US state-level panel data on infrastructure spending and on per capita income inequality from 1950 to 2010, this paper sets out to test whether an empirical link exists between infrastructure and inequality. Panel regressions with fixed effects show that an increase in the growth rate of spending on highways and higher education in a given decade correlates negatively with Gini indices at the end of the decade, thus suggesting a causal effect from growth in infrastructure spending to a reduction in inequality through better access to education and opportunities for employment. More significantly, this relationship is more pronounced with inequality at the bottom 40 percent of the income distribution. In addition, infrastructure expenditures on highways are shown to be more effective at reducing inequality. By carrying out a counterfactual experiment, the results show that those US states with a significantly higher bottom Gini coefficient in 2010 had underinvested in infrastructure during the previous decade. From a policy-making perspective, new innovations in finance for infrastructure investments are developed, for the US, other industrially advanced countries and also for developing economies.

E-learning has become an integral part of higher education, significantly influencing the teaching and learning landscape. This study investigates the impact of student characteristics such as gender, grade, and major on E-learning satisfaction. Utilizing Structural Equation Modeling (SEM) and collecting data through 527 valid questionnaires from Nanjing Normal University students, this research reveals the nuanced relationships between these variables and E-learning satisfaction. The findings indicate that gender, grade, and major significantly and positively impact student satisfaction with E-learning, highlighting the need for tailored E-learning resources to meet diverse student needs. The study underscores the importance of continuous improvement in E-learning resources and platforms to enhance student satisfaction. This research contributes to the understanding of effective E-learning strategies in higher education institutions.

Road accidents involving motorcyclists significantly threaten sustainable mobility and community safety, necessitating a comprehensive examination of contributing factors. This study investigates the behavioral aspects of motorcyclists, including riding anger, sensation-seeking, and mindfulness, which play crucial roles in road accidents. The study employed structural equation modeling to analyze the data, utilizing a cross-sectional design and self-administered questionnaires. The results indicate that riding anger and sensation-seeking tendencies have a direct impact on the likelihood of road accidents, while mindfulness mitigates these effects. Specifically, mindfulness partially mediates the relationships between riding anger and road accident proneness, as well as between sensation-seeking and road accident proneness. These findings underscore the importance of effective anger management, addressing sensation-seeking tendencies, and promoting mindfulness practices among motorcyclists to enhance road safety and sustainable mobility. The insights gained from this research are invaluable for relevant agencies and stakeholders striving to reduce motorcycle-related accidents and foster sustainable communities through targeted interventions and educational programs.

This study uses a Time-Varying Parameter Stochastic Volatility Vector Autoregression (TVP-SV-VAR) model to conduct an empirical analysis of the dynamic effects of China’s stock market volatility on the agricultural loan market and its channels. The results show that the relationship between stock market and agricultural loan market volatility is time varying and is always positive. The investor sentiment is a major conduit through which the effect takes place. This time-varying effect and transmission mechanism are most apparent between 2011 and 2017 and have since waned and stabilized. These have significant implications for the stable and orderly development of the agricultural loan market, highlighting the importance of the sound financial market system and timely policy, better market monitoring and early warning system and the formation of a mature and sound agricultural credit mechanism.

Using data from 31 provinces, municipalities, and autonomous regions in mainland China from 2006 to 2019, we employ a double difference (DID) model and a spatial double difference (SDID) model to estimate the impact of the High-speed Railway (HSR) on the income gap between urban and rural residents, as well as its spatial spillover effects. Our research reveals several key findings. Firstly, the introduction of high-speed railways helps to narrow the income gap between urban and rural residents within local areas, but its spatial effects can lead to an increase in the income gap in neighboring provinces. Secondly, from a spatial perspective, intermediate variables such as industrial structure, education, science and technology, and foreign trade can also contribute to balancing the income gap between urban and rural residents, although the impact of population mobility is not significant. Thirdly, further analysis of the spatial effects demonstrates that education plays a significant role in balancing the income gap both within the local province and neighboring provinces. Additionally, adjustments in industrial structure, advancements in science and technology, and foreign trade have stronger spillover effects in reducing the income gap among neighboring provinces compared to their impact at a local level.