Community detection plays a pivotal role in uncovering closely connected subgraphs, aiding various real-world applications such as recommendation systems and anomaly detection. With the surge of rich information available for entities in real-world networks, the community detection problem in attributed networks has attracted widespread attention. While previous research has effectively leveraged network topology and attribute information for attributed community detection, these methods overlook two critical issues: (i) the semantic similarity between node attributes within the community, and (ii) the inherent mesoscopic structure, which differs from the pairwise connections of the micro-structure. To address these limitations, we propose HACD, a novel attributed community detection model based on heterogeneous graph attention networks. HACD treats node attributes as another type of node, constructs attributed networks into heterogeneous graph structures and employs attribute-level attention mechanisms to capture semantic similarity. Furthermore, HACD introduces a community membership function to explore mesoscopic community structures, enhancing the robustness of detected communities. Extensive experiments demonstrate the effectiveness and efficiency of HACD, outperforming state-of-the-art methods in attributed community detection tasks. Our code is publicly available at https://github.com/Anniran1/HACD1-wsdm https://github.com/Anniran1/HACD1-wsdm.

Accurately predicting agricultural product prices is crucial for the stability of the agricultural market. However, due to the collection intervals of agricultural price data, which are typically daily, weekly, or monthly, the data volume is relatively small. This limitation affects the accuracy of deep learning models in price prediction. Data augmentation is an effective method to improve the accuracy of agricultural price predictions. This research proposes a novel data augmentation model, EMD-TCN-TimeGAN. Based on TimeGAN, this model has been significantly improved by replacing the RNN-based components with TCN, which enhances the model’s ability to capture long-term dependencies. Additionally, the model incorporates an EMD module to decompose the original price series, thereby better capturing the intrinsic structural information of the time series and further improving the quality of the generated data. Experiments conducted on a collected corn dataset show that adding the augmented data to the training set of the prediction model and retraining it significantly improves the prediction accuracy. The coefficient of determination (R2) increased from 0.928831 to 0.968742, and the mean absolute error (MAE) decreased from 0.026023 to 0.016628. Comparisons with the TimeGAN model using RNN components validate the effectiveness of replacing the components with TCN; comparisons with TCN-TimeGAN validate the effectiveness of the EMD module in further improving prediction performance. The EMD-TCN-TimeGAN proposed in this study generates sequences that better preserve the temporal dynamics of the time series data, maintaining the temporal relationships between the original variables. This improves the accuracy of small-sample agricultural price predictions, which is of significant importance and benefit to agricultural production and related activities.

The wind speed exhibits by diverse periodicity and trend, directly inputting the wind speed sequence into the model to forecast significantly impacts the prediction accuracy. By using decomposition algorithms to decompose the wind speed sequence, the decomposed sequence serves as additional variables. Modeling with these decomposed components, along with factors such as temperature, humidity, wind direction, and dew point temperature, can enhance prediction accuracy. This paper focuses on wind speed as the research target, collecting influencing factors such as temperature, humidity, wind direction, and dew point temperature. VMD (variational mode decomposition) is utilized to decompose the wind speed into multiple components. These decomposed components, along with the collected influencing factors, are jointly used as features inputted into the TDformer model for wind speed prediction. Additionally, TSMixer is employed to enhance the trend prediction module of TDformer. Through ablation experiments and comparative experiments, the results indicate: (1) VMD leads to a decrease of over 40% in MAE and MSE. (2) Utilizing TSMixer to improve TDformer results in a decrease of 3%-20% in MAE and MSE. Moreover, the improved model exhibits over 8% improvement in MAE and MSE metrics compared to other time series forecasting models on this dataset.

Long-term forecasting of wheat prices is important for agricultural production, market policy making and food security assurance. In this study, an improved long time series forecasting model for wheat price, DWT-TimesNet, is proposed, which is deeply improved on the basis of the original TimesNet model. The main improvement lies in the use of Discrete Wavelet Transformation (DWT) instead of the original Fast Fourier Transformation (FFT) for time series decomposition. Since the FFT has certain limitations in dealing with non-smooth signals, such as fixed frequency resolution and the inability to provide time and frequency information at the same time, the DWT overcomes these shortcomings through the characteristics of multi-resolution analysis, and is able to localize signals at different scales and provide a more refined time-frequency representation. In the improved DWT-TimesNet model, we use the mean plus standard deviation method to dynamically determine a threshold that is used to filter valid cycles, and cycles corresponding to amplitudes above this threshold are considered valid cycles. This improvement allows the model to be more flexible in adapting to signal variations, and improves the model’s ability to capture the periodic properties of the signal compared to the fixed cycle selection mechanism in the original method. Furthermore, the improved method returns an additional parameter k indicating the number of selected cycles, which provides more information for subsequent processing and increases the interpretability of the method. To validate the effectiveness of the DWT-TimesNet model, we compare it with the original TimesNet model and other mainstream time series forecasting models. The experimental results show that the DWT-TimesNet model achieves remarkable results in wheat price forecasting, with results far ahead of other models. This research is not only academically significant, but also has important implications and benefits for practical production and life. The accurate prediction of wheat prices can help farmers rationalize their planting plans and reduce production costs; the government can formulate reasonable market policies based on the prediction results and stabilize market prices; and it also helps to achieve food security guarantee.

To improve the quality prediction accuracy of typical workpiece in discrete manufacturing, an optimized feature construction method is proposed, which is combined with the XGBoost algorithm to reduce the overfitting degree of the quality conformance prediction model and improve the prediction accuracy. As for the feature engineering, grouping statistics and frequency table coding methods are used to reconstruct new statistical features, and 30 features with high correlation are screened out by the Chis-quare test and Pearson correlation coefficient. After comparing and analyzing five kinds of different algorithmic models, the experimental results show that the typical workpieces quality prediction model based on feature reconstruction and XGBoost algorithm has superior prediction accuracy and online scores. The prediction method provides a practical basis and reference for quality prediction in discrete manufacturing processes.

The study focuses on the transaction risk faced by consumers when it comes to cross-border online shopping. On the process of shopping cross border online, the overseas purchasing agent was set as the basic in this study. Then, dataset is used to verify the application of KMV model in cross-border e-commerce transaction risk. The store risk indicators of overseas purchasing agent is divided into five types. It is operating duration, rate of return and replacement, number of positive comments, the seller's reputation, and sales. The entropy weight method is used to determine the weight of each indicator, and then KMV model is given a new meaning. Finally, through experiment verification and analysis, KMV has a good early warning effect on the transaction risk of cross-border online shopping. The higher the seller's reputation is, the smaller probability od a store's transaction risk will be. The number of positive comments and sales as same as the seller's reputation. However, if the rate of return and replacement is high, the probability of a store's transaction risk will also be high. Although the indicator of the rate of return and replacement has a low weight, it is still very important.

This paper is to propose an improved algorithm in modeling user consumption behavior, which combined Logistic regression and XGBoost algorithm to predict users' purchasing behavior in an e-commerce website.XGBoost, as a feature transformation, is used to make sample prediction. According to the prediction results, the information of each regression tree will construct the new feature vector, which will be the input data of the logistic regression model. The previous improved clustering algorithm [1] will be involved to cluster the different user divisions for further comparative analysis with the three predictive models in this paper.Specifically, more than 50 million original data are collected and preprocessed for correlation mining. 60% are selected randomly to be the training set and 20% to be the verification set and the rest 20% as the test set. Logistic regression and XGBoost algorithm are used respectively to set up two models based on making use of the advantages of each. The research shows that Logistic regression on XGBoost method is feasible and the evaluation index of the model is better than any methods being used alone.

Given the complexity of macro-economic situation, in the decision-making of monetary policy, it is vital to first grasp and then effectively manage and guide the public expectations. However, expectation is an index hard to measure. With the emergence of big data application, measuring expectations through constructing Internet public opinion index has become an important research direction. According to the characteristics of monetary policy expectations, this paper determines the relevant key words, conducts research on online public opinions by mining and crawling the netnews and search data, and construct the expectations index on monetary policy. The practicability of the expectations index is then verified by measuring its correlation with the macroeconomic variables. The result indicates that the index can indeed represent the public expectations, which means it can be applied to analyze the pattern of public expectations on the monetary policy. Apart from that, the fact that it changes ahead of the price variable can serve as the basis for farsighted decisions.