Integrating Advanced Neural Techniques in Educational Data: Attention-Enhanced LSTM and AGCN for Time Series and Clustering Analysis

With the rapid development of artificial intelligence and machine learning across various domains, their application in educational data analysis has gained increasing attention. This paper proposes a method that combines Attention-Enhanced Long Short-Term Memory Networks (LSTM) and Adaptive Graph Convolutional Networks (AGCN) to meet the specific needs of educational data analysis. Our goal is to deeply explore and analyze the educational funding data in Western China using these advanced techniques, aiming to uncover time series trends and hidden group patterns. Our analysis of educational funding data reveals that the attention-enhanced LSTM significantly improves the processing of time series data, especially in cap-turing dynamic changes and important features over time. The adaptive graph convolutional network effectively unveils complex relationships between different educational entities, providing a new perspective for cluster analysis. Integrating these two techniques, our method can more accurately predict and interpret the trends in educational funding allocation, offering valuable insights for policy makers. The experimental results demonstrate the effectiveness of our proposed method in educational data analysis, particularly in terms of prediction accuracy and pattern recognition. This research not only extends the application of neural network technology in the field of education but also provides data support for the formulation and optimization of educational policies.