Visualization analysis of educational data statistics based on big data mining.

The article focuses on improving the visual analysis of educational data statistics through a big data mining approach to enhance students' academic performance. It introduces an improved Fuzzy C-Means (FCM) clustering algorithm incorporating Mahalanobis distance and covariance matrix to effectively mine valuable educational data while eliminating correlations among data types. The mined data are then visually laid out using an enhanced force-guided (FR) layout algorithm, with results presented via the ECharts visualization component, enabling clearer statistical analysis and interaction. Experimental results from a university dataset show that learning analysis data constitute the largest proportion (15%) of valuable educational data, and the improved visualization method reduces layout overlaps, enhancing clarity. The study concludes that this method facilitates more accurate and intuitive educational data analysis, supporting teaching plan formulation, while noting the need for finer-grained data collection in future research.