You are required to read and agree to the below before accessing a full-text version of an article in the IDE article repository.

The full-text document you are about to access is subject to national and international copyright laws. In most cases (but not necessarily all) the consequence is that personal use is allowed given that the copyright owner is duly acknowledged and respected. All other use (typically) require an explicit permission (often in writing) by the copyright owner.

For the reports in this repository we specifically note that

  • the use of articles under IEEE copyright is governed by the IEEE copyright policy (available at
  • the use of articles under ACM copyright is governed by the ACM copyright policy (available at
  • technical reports and other articles issued by M‰lardalen University is free for personal use. For other use, the explicit consent of the authors is required
  • in other cases, please contact the copyright owner for detailed information

By accepting I agree to acknowledge and respect the rights of the copyright owner of the document I am about to access.

If you are in doubt, feel free to contact

iXGB: Improving the Interpretability of XGBoost using Decision Rules and Counterfactuals

Publication Type:

Conference/Workshop Paper


16th International Conference Agents and Artificial Intelligence


Tree-ensemble models, such as Extreme Gradient Boosting (XGBoost), are renowned Machine Learning mod- els which have higher prediction accuracy. This higher accuracy, however, comes at the cost of reduced inter- pretability compared to traditional tree-based models. Also, the decision path or prediction rule of XGBoost is not explicit like the tree-based models. This paper proposes the iXGB – interpretable XGBoost, an approach to improve the interpretability of XGBoost. iXGB approximates a set of rules from the internal structure of XGBoost and the characteristics of the data. In addition, iXGB generates a set of counterfactuals from the neighbourhood of the test instances to support the understanding of the end-users on their operational rele- vance. The performance of iXGB in generating rule sets is evaluated with experiments on real and benchmark datasets which demonstrated reasonable interpretability. The evaluation result also supports that the inter- pretability of XGBoost can be improved without using surrogate methods.


author = {Mir Riyanul Islam and Mobyen Uddin Ahmed and Shahina Begum},
title = {iXGB: Improving the Interpretability of XGBoost using Decision Rules and Counterfactuals},
month = {March},
year = {2024},
booktitle = {16th International Conference Agents and Artificial Intelligence},
url = {}