Student exam pass prediction (EPP) is a key task in educational assessment and can help teachers identify students’ learning obstacles in a timely manner and optimize teaching strategies. However, existing EPP models, although capable of providing quantitative analysis, suffer from issues such as complex algorithms, poor interpretability, and unstable accuracy. Moreover, the evaluation process is opaque, making it difficult for teachers to understand the basis for scoring. To address this, this paper proposes an approximate belief rule base (ABRB-a) student examination passing prediction method based on adaptive reference point selection using symmetry. Firstly, a random forest method based on cross-validation is adopted, introducing intelligent preprocessing and adaptive tuning to achieve precise screening of multi-attribute features. Secondly, reference points are automatically generated through hierarchical clustering algorithms, overcoming the limitations of traditional methods that rely on prior expert knowledge. By organically combining IF-THEN rules with evidential reasoning (ER), a traceable decision-making chain is constructed. Finally, a projection covariance matrix adaptive evolution strategy (P-CMA-ES-M) with Mahalanobis distance constraints is introduced, significantly improving the stability and accuracy of parameter optimization. Through experimental analysis, the ABRB-a model demonstrates significant advantages over existing models in terms of accuracy and interpretability.

Concrete compressive strength is a key indicator for measuring structural performance and durability. Its accurate prediction is essential for engineering safety and construction quality. However, concrete strength is influenced by many material and environmental factors, making it nonlinear and uncertain. The evidential reasoning (ER) rule is effective in predicting strength in complex systems due to its ability to handle uncertainty and combine multiple data sources. However, existing ER methods have limitations when applied to concrete strength prediction. Specifically, the belief distribution does not fully capture the nonlinear causal relationship between the input features and compressive strength, and the reliability calculation method is relatively simple, making it difficult to reflect the anomalies and uncertainties in the data comprehensively. Furthermore, model parameter optimization is insufficient for achieving high-precision predictions. To address these issues, this paper proposes a concrete compressive strength prediction method based on the causal evidential reasoning (CER) rule. First, a causal matrix is introduced in the initial stage to more effectively represent the causal relationship between the original features and the prediction target. Second, three reliability calculation methods are designed, and a combined reliability is obtained through a game theory mechanism to improve the model’s ability to handle uncertain information. Third, in the model optimization stage, the whale optimization algorithm (WOA) is used to optimize the causal matrix and attribute weights. Experimental results on a concrete compressive strength dataset demonstrate the effectiveness and advantages of the proposed method.