Explainable artificial intelligence (XAI) is essential for fostering trust, transparency, and accountability in machine learning systems, particularly when applied in high-stakes domains. This paper introduces a novel XAI system designed for classification tasks on tabular data, which offers a balance between performance and interpretability. The proposed method, GlassBoost, first trains an XGBoost model on a given dataset and then computes gain scores, quantifying the average improvement in the model’s loss function contributed by each feature during tree splits. Based on these scores, a subset of significant features is selected. A shallow decision tree is then trained using the top d features with the highest gain scores, where d is significantly smaller than the total number of original features. This model compression yields a transparent, IF–THEN rule-based decision process that remains faithful to the original high-performing model. To evaluate the system, we apply it to an anomaly detection task in the context of intrusion detection systems (IDSs), using a dataset containing traffic features from both malicious and normal activities. Results show that our method achieves high accuracy, precision, and recall while providing a clear and interpretable explanation of its decision-making. We further validate its explainability using SHAP, a well-established approach in the field of XAI. Comparative analysis demonstrates that GlassBoost outperforms SHAP in terms of precision, recall, and accuracy, with more balanced performance across the three metrics. Likewise, our review of literature findings indicate that Glassboost outperforms many other XAI models while retaining computational efficiency. In one of our configurations, GlassBoost achieved accuracy of 0.9868, recall of 0.9792, and precision of 0.9843 using only eight features within a tree structure of a maximum depth of four.
The structural integrity of pressure vessels (PVs) is controlled by the application of various design and fabrication codes and standards. Within the European single market (ESM) design codes exist at both a European and a national level which can lead to variability in design procedures. The European standard EN 13445 has been updated several times to modify the design curves based on analytical modelling of high strength materials. The design curves in EN 13445 now differ significantly from those presented in the British national code that preceded it, namely PD 5500. As a result higher minimum Charpy test temperatures (T27J) are found using the EN 13445 procedure in comparison to those derived using the PD 5500 procedure. While the PD 5500 design curves have been validated experimentally it is generally accepted that they are overly conservative. This inherent conservatism in PD 5500 may account for some of the differences in the minimum Charpy test temperature, the analytical model used to generate the EN 13445 design curves however was validated with data from high strength steels only (σy ≥ 420 MPa). It is not clear that the results can be applied directly to low/medium strength materials. This work identifies some of the disparities between the EN 13445 and PD 5500 procedures, for low temperature applications. A programme of work, at Imperial College London, is described. This programme of work, currently underway, is aimed at addressing concerns about the robustness of the updated EN 13445 design curves, especially for lower-strength steels in the as-welded condition.