Symmetry-Aware Causal-Inference-Driven Web Performance Modeling: A Structure-Aware Framework for Predictive Analysis and Actionable Optimization

Understanding and improving web performance is essential for enhancing user experience, yet existing approaches remain largely correlation-based and lack causal interpretability. To address this limitation, we propose a causal-inference-driven framework for diagnosing and optimizing user-centric Web Vitals such as Largest Contentful Paint (LCP), First Input Delay (FID), and Cumulative Layout Shift (CLS). Our contributions are threefold. (1) We construct a comprehensive feature representation that captures Document Object Model (DOM) structure, resource loading behaviors, rendering characteristics, and JavaScript execution, integrating browser-level domain knowledge into the modeling pipeline. (2) We introduce a hybrid causal discovery method that combines constraint-based reasoning with differentiable score-based learning to estimate high-dimensional causal structures reflecting real rendering processes. (3) We develop a causal-effect-based intervention optimization module that leverages counterfactual reasoning to identify actionable modifications for performance improvement. Our framework further leverages structural symmetries inherent in rendering processes, using repeated layout patterns and invariant dependency flows to reduce redundancy and strengthen the stability and identifiability of causal discovery. Extensive experiments on HTTP Archive, Chrome UX Report (CrUX), and a synthetic ground truth dataset demonstrate that our framework achieves higher causal accuracy, more stable predictive performance, more effective intervention recommendations, and improved interpretability compared with existing rule-based, statistical, and machine learning baselines. These results highlight the potential of causality-aware analysis for practical web performance optimization.