A Review of Interpretability Methods for Gradient Boosting Decision Trees
DOI:
https://doi.org/10.5753/jbcs.2025.5324Keywords:
Explainability, Interpretability, Gradient Boosting Decision Trees, Machine LearningAbstract
This survey examines interpretability methods used or proposed for Gradient Boosting Decision Trees, which are advanced machine learning algorithms based on decision trees. The studies analyzed were gathered using synonyms for "explainability" combined with synonyms for "method," as well as synonyms for "Gradient Boosting Decision Trees." The proposed or applied approaches are classified by their techniques and described in detail. Among these methods, we recommend using SHAP values to rank features based on their relevance, as this approach aligns well with the structure of Gradient Boosting Decision Trees. Additionally, we suggest considering inTrees, RULECOSI+, and Tree Space Prototypes when applicable.
Downloads
References
Adadi, A. and Berrada, M. (2018). Peeking Inside the Black-Box: A Survey on Explainable Artificial Intelligence (XAI). IEEE Access, 6:52138-52160. DOI: 10.1109/ACCESS.2018.2870052.
Aguilar-Palacios, C., Munoz-Romero, S., and Rojo-Alvarez, J. L. (2020). Cold-Start Promotional Sales Forecasting through Gradient Boosted-Based Contrastive Explanations. IEEE Access, 8:137574-137586. DOI: 10.1109/ACCESS.2020.3012032.
Alex Goldstein, Adam Kapelner, J. B. and Pitkin, E. (2015). Peeking inside the black box: Visualizing statistical learning with plots of individual conditional expectation. Journal of Computational and Graphical Statistics, 24(1):44-65. DOI: 10.1080/10618600.2014.907095.
Aljadani, A., Alharthi, B., Farsi, M., Balaha, H., Badawy, M., and Elhosseini, M. (2023). Mathematical Modeling and Analysis of Credit Scoring Using the LIME Explainer: A Comprehensive Approach. Mathematics, 11(19). DOI: 10.3390/math11194055.
Apley, D. W. and Zhu, J. (2020). Visualizing the effects of predictor variables in black box supervised learning models. Journal of the Royal Statistical Society Series B: Statistical Methodology, 82(4):1059-1086. DOI: 10.1111/rssb.12377.
Barredo Arrieta, A., DÃaz-RodrÃguez, N., Del Ser, J., Bennetot, A., Tabik, S., Barbado, A., Garcia, S., Gil-Lopez, S., Molina, D., Benjamins, R., Chatila, R., and Herrera, F. (2020). Explainable Artificial Intelligence (XAI): Concepts, taxonomies, opportunities and challenges toward responsible AI. Inf. Fusion, 58(C):82-115. DOI: 10.1016/j.inffus.2019.12.012.
Başağaoğlu, H., Chakraborty, D., Do Lago, C., Gutierrez, L., Şahinli, M., Giacomoni, M., Furl, C., Mirchi, A., Moriasi, D., and Şengör, S. (2022). A Review on Interpretable and Explainable Artificial Intelligence in Hydroclimatic Applications. Water (Switzerland), 14(8). DOI: 10.3390/w14081230.
Bedi, S., Samal, A., Ray, C., and Snow, D. (2020). Comparative evaluation of machine learning models for groundwater quality assessment. Environmental Monitoring and Assessment, 192(12). DOI: 10.1007/s10661-020-08695-3.
Bharati, S., Mondal, M. R. H., and Podder, P. (2023). A Review on Explainable Artificial Intelligence for Healthcare: Why, How, and When? IEEE Transactions on Artificial Intelligence, pages 1-15. DOI: 10.1109/TAI.2023.3266418.
Boulitsakis Logothetis, S., Green, D., Holland, M., and Al Moubayed, N. (2023). Predicting acute clinical deterioration with interpretable machine learning to support emergency care decision making. Scientific Reports, 13(1). DOI: 10.1038/s41598-023-40661-0.
Breiman, L. (1996). Bagging predictors. Machine Learning, 24:123-140. DOI: 10.1007/BF00058655.
Burkart, N. and Huber, M. F. (2021). A Survey on the Explainability of Supervised Machine Learning. J. Artif. Int. Res., 70:245-317. DOI: 10.1613/jair.1.12228.
Calderón-Díaz, M., Silvestre Aguirre, R., Vásconez, J. P., Yáñez, R., Roby, M., Querales, M., and Salas, R. (2024). Explainable Machine Learning Techniques to Predict Muscle Injuries in Professional Soccer Players through Biomechanical Analysis. Sensors, 24(1). DOI: 10.3390/s24010119.
Carvalho, D. V., Pereira, E. M., and Cardoso, J. S. (2019). Machine learning interpretability: A survey on methods and metrics. 8(8). DOI: 10.3390/electronics8080832.
Chen, T. and Guestrin, C. (2016). Xgboost: A scalable tree boosting system. CoRR, abs/1603.02754. DOI: 10.1145/2939672.2939785.
Christodoulou, E. and Gregoriades, A. (2023). Applying Machine Learning in Personality-based Persuasion Marketing. In 2023 IEEE International Conference on Data Mining Workshops (ICDMW), pages 16-23. DOI: 10.1109/ICDMW60847.2023.00010.
Chu, L., Nelen, J., Crivellari, A., Masiliūnas, D., Hein, C., and Lofi, C. (2024). Relationships between geo-spatial features and COVID-19 hospitalisations revealed by machine learning models and SHAP values. International Journal of Digital Earth, 17(1). DOI: 10.1080/17538947.2024.2358851.
Covert, I., Lundberg, S., and Lee, S.-I. (2022). Explaining by removing: A unified framework for model explanation.
Das, S., Agarwal, N., Venugopal, D., Sheldon, F. T., and Shiva, S. (2020). Taxonomy and Survey of Interpretable Machine Learning Method. In 2020 IEEE Symposium Series on Computational Intelligence (SSCI), pages 670-677. DOI: 10.1109/SSCI47803.2020.9308404.
De Bock, K., Coussement, K., Caigny, A., Słowińskii, R., Baesens, B., Boute, R., Choi, T.-M., Delen, D., Kraus, M., Lessmann, S., Verbeke, W., and Weber, R. (2023). Explainable AI for Operational Research: A defining framework, methods, applications, and a research agenda. European Journal of Operational Research. DOI: 10.1016/j.ejor.2023.09.026.
de Oliveira, R. and Martens, D. (2021). A framework and benchmarking study for counterfactual generating methods on tabular data. Applied Sciences (Switzerland), 11(16). DOI: 10.3390/app11167274.
Delgado-Panadero, Á., Hernández-Lorca, B., García-Ordás, M. T., and Benítez-Andrades, J. A. (2022). Implementing local-explainability in Gradient Boosting Trees: Feature Contribution. Inf. Sci., 589(C):199-212. DOI: 10.1016/j.ins.2021.12.111.
Deng, H. (2014). Interpreting Tree Ensembles with inTrees. CoRR. DOI: 10.48550/arXiv.1408.5456.
Doshi-Velez, F. and Kim, B. (2017). Towards a rigorous science of interpretable machine learning. DOI: 10.48550/arXiv.1702.08608.
Du, J., Chang, X., Ye, C., Zeng, Y., Yang, S., Wu, S., and Li, L. (2023). Developing a hypertension visualization risk prediction system utilizing machine learning and health check-up data. Scientific Reports, 13(1). DOI: 10.1038/s41598-023-46281-y.
Feng, J., Zhang, H., Gao, K., Liao, Y., Yang, J., and Wu, G. (2022). A machine learning and game theory-based approach for predicting creep behavior of recycled aggregate concrete. Case Studies in Construction Materials, 17. DOI: 10.1016/j.cscm.2022.e01653.
Fisher, A., Rudin, C., and Dominici, F. (2019). All models are wrong, but many are useful: Learning a variable's importance by studying an entire class of prediction models simultaneously.
Freund, Y. and Schapire, R. E. (1997). A Decision-Theoretic Generalization of On-Line Learning and an Application to Boosting. Journal of Computer and System Sciences, 55(1):119-139. DOI: 10.1006/jcss.1997.1504.
Friedman, J. H. (2001). Greedy function approximation: A gradient boosting machine. The Annals of Statistics, 29(5):1189 - 1232. DOI: 10.1214/aos/1013203451.
GhoshRoy, D., Alvi, P., and Santosh, K. (2023). Explainable AI to Predict Male Fertility Using Extreme Gradient Boosting Algorithm with SMOTE. Electronics (Switzerland), 12(1). DOI: 10.3390/electronics12010015.
Giudici, P. and Raffinetti, E. (2021). Shapley-Lorenz eXplainable Artificial Intelligence. Expert Systems with Applications, 167. DOI: 10.1016/j.eswa.2020.114104.
Gramegna, A. and Giudici, P. (2020). Why to buy insurance? An explainable artificial intelligence approach. Risks, 8(4):1-9. DOI: 10.3390/risks8040137.
Guidotti, R., Monreale, A., Ruggieri, S., Turini, F., Giannotti, F., and Pedreschi, D. (2018). A survey of methods for explaining black box models. ACM Computing Surveys, 51(5). DOI: 10.1145/3236009.
Hara, S. and Hayashi, K. (2017). Making tree ensembles interpretable: A bayesian model selection approach.
He, S., Niu, G., Sang, X., Sun, X., Yin, J., and Chen, H. (2023). Machine Learning Framework with Feature Importance Interpretation for Discharge Estimation: A Case Study in Huitanggou Sluice Hydrological Station, China. Water (Switzerland), 15(10). DOI: 10.3390/w15101923.
Herrera, G. P., Constantino, M., Su, J.-J., and Naranpanawa, A. (2023). The use of ICTs and income distribution in Brazil: A machine learning explanation using SHAP values. Telecommun. Policy, 47(8). DOI: 10.1016/j.telpol.2023.102598.
Ho, I.-T., Matysik, M., Herrera, L., Yang, J., Guderlei, R., Laussegger, M., Schrantz, B., Hammer, R., Miranda-Quintana, R., and Smiatek, J. (2022). Combination of explainable machine learning and conceptual density functional theory: applications for the study of key solvation mechanisms. Physical Chemistry Chemical Physics, 24(46):28314-28324. DOI: 10.1039/d2cp04428e.
Islam, S. R., Eberle, W., Ghafoor, S. K., and Ahmed, M. (2021). Explainable artificial intelligence approaches: A survey. DOI: 10.48550/arXiv.2101.09429.
Jas, K., Mangalathu, S., and Dodagoudar, G. R. (2024). Evaluation and analysis of liquefaction potential of gravelly soils using explainable probabilistic machine learning model. Computers and Geotechnics, 167. DOI: 10.1016/j.compgeo.2023.106051.
Ke, G., Meng, Q., Finley, T., Wang, T., Chen, W., Ma, W., Ye, Q., and Liu, T.-Y. (2017). LightGBM: a highly efficient gradient boosting decision tree. In Proceedings of the 31st International Conference on Neural Information Processing Systems, NIPS'17, pages 3149-3157, Red Hook, NY, USA. Curran Associates Inc.. DOI: 10.5555/3294996.3295074.
Kök, I., Okay, F. Y., Muyanlı, Ö., and Özdemir, S.. (2023). Explainable Artificial Intelligence (XAI) for Internet of Things: A Survey. IEEE Internet of Things Journal, 10(16):14764-14779. DOI: 10.1109/JIOT.2023.3287678.
Kookalani, S., Cheng, B., and Torres, J. (2022a). Structural performance assessment of GFRP elastic gridshells by machine learning interpretability methods. Frontiers of Structural and Civil Engineering, 16(10):1249-1266. DOI: 10.1007/s11709-022-0858-5.
Kookalani, S., Nyunn, S., and Xiang, S. (2022b). Form-finding of lifting self-forming GFRP elastic gridshells based on machine learning interpretability methods. Structural Engineering and Mechanics, 84(5):605-618. DOI: 10.12989/sem.2022.84.5.605.
Lazaridis, P., Kavvadias, I., Demertzis, K., Iliadis, L., and Vasiliadis, L. (2023). Interpretable Machine Learning for Assessing the Cumulative Damage of a Reinforced Concrete Frame Induced by Seismic Sequences. Sustainability (Switzerland), 15(17). DOI: 10.3390/su151712768.
Li, Y., Jia, C., Chen, H., Su, H., Chen, J., and Wang, D. (2023a). Machine Learning Assessment of Damage Grade for Post-Earthquake Buildings: A Three-Stage Approach Directly Handling Categorical Features. Sustainability (Switzerland), 15(18). DOI: 10.3390/su151813847.
Li, Z., Zhu, Y., and Van Leeuwen, M. (2023b). A Survey on Explainable Anomaly Detection. ACM Transactions on Knowledge Discovery from Data, 18(1). DOI: 10.1145/3609333.
Liang, S., Shen, Y., and Ren, X. (2022). Comparative study of influential factors for punching shear resistance/failure of RC slab-column joints using machine-learning models. Structures, 45:1333-1349. DOI: 10.1016/j.istruc.2022.09.110.
Liu, Y., Huang, F., Ma, L., Zeng, Q., and Shi, J. (2024). Credit scoring prediction leveraging interpretable ensemble learning. Journal of Forecasting, 43(2):286-308. DOI: 10.1002/for.3033.
Lundberg, S., Erion, G., Chen, H., DeGrave, A., Prutkin, J., Nair, B., Katz, R., Himmelfarb, J., Bansal, N., and Lee, S.-I. (2020). From local explanations to global understanding with explainable AI for trees. Nature Machine Intelligence, 2(1):56-67. DOI: 10.1038/s42256-019-0138-9.
Lundberg, S. and Lee, S.-I. (2017). A unified approach to interpreting model predictions. DOI: 10.48550/arXiv.1705.07874.
Lundberg, S. M., Erion, G. G., and Lee, S.-I. (2019). Consistent individualized feature attribution for tree ensembles. DOI: 10.48550/arXiv.1802.03888.
Lv, H., Li, H., Chen, Y., and Feng, T. (2023). An origin-destination level analysis on the competitiveness of bike-sharing to underground using explainable machine learning. Journal of Transport Geography, 113. DOI: 10.1016/j.jtrangeo.2023.103716.
Ma, C., Wang, S., Zhao, J., Xiao, X., Xie, C., and Feng, X. (2023a). Prediction of shear strength of RC deep beams based on interpretable machine learning. Construction and Building Materials, 387. DOI: 10.1016/j.conbuildmat.2023.131640.
Ma, C., Wang, W., Wang, S., Guo, Z., and Feng, X. (2023b). Prediction of shear strength of RC slender beams based on interpretable machine learning. Structures, 57. DOI: 10.1016/j.istruc.2023.105171.
Minh, D., Wang, H. X., Li, Y. F., and Nguyen, T. N. (2022). Explainable artificial intelligence: a comprehensive review. Artificial Intelligence Review, 55(5):3503-3568. DOI: 10.1007/s10462-021-10088-y.
Moustafa, N., Koroniotis, N., Keshk, M., Zomaya, A., and Tari, Z. (2023). Explainable Intrusion Detection for Cyber Defences in the Internet of Things: Opportunities and Solutions. IEEE Communications Surveys and Tutorials, 25(3):1775-1807. DOI: 10.1109/COMST.2023.3280465.
Nadeem, A., Vos, D., Cao, C., Pajola, L., Dieck, S., Baumgartner, R., and Verwer, S. (2023). SoK: Explainable Machine Learning for Computer Security Applications. In 2023 IEEE 8th European Symposium on Security and Privacy (EuroS&P), pages 221-240. DOI: 10.1109/EuroSP57164.2023.00022.
Nagahisarchoghaei, M., Nur, N., Cummins, L., Nur, N., Karimi, M., Nandanwar, S., Bhattacharyya, S., and Rahimi, S. (2023). An Empirical Survey on Explainable AI Technologies: Recent Trends, Use-Cases, and Categories from Technical and Application Perspectives. Electronics (Switzerland), 12(5). DOI: 10.3390/electronics12051092.
Nguyen, H., Viviani, J.-L., and Ben Jabeur, S. (2023). Bankruptcy prediction using machine learning and Shapley additive explanations. Review of Quantitative Finance and Accounting. DOI: 10.1007/s11156-023-01192-x.
Obregon, J. and Jung, J.-Y. (2023). RuleCOSI+: Rule extraction for interpreting classification tree ensembles. Inf. Fusion, 89(C):355-381. DOI: 10.1016/j.inffus.2022.08.021.
Obregon, J., Kim, A., and Jung, J. Y. (2019). RuleCOSI: Combination and simplification of production rules from boosted decision trees for imbalanced classification. Expert Systems with Applications, 126:64-82. DOI: 10.1016/j.eswa.2019.02.012.
Prokhorenkova, L., Gusev, G., Vorobev, A., Dorogush, A. V., and Gulin, A. (2019). Catboost: unbiased boosting with categorical features. DOI: 10.48550/arXiv.1706.09516.
Quinlan, J. R. (1993). Chapter 2 - constructing decision trees. In Quinlan, J. R., editor, C4.5, pages 17-26. Morgan Kaufmann, San Francisco (CA). DOI: 10.1016/B978-0-08-050058-4.50007-3.
Rawal, A., McCoy, J., Rawat, D. B., Sadler, B. M., and Amant, R. S. (2022). Recent Advances in Trustworthy Explainable Artificial Intelligence: Status, Challenges, and Perspectives. IEEE Transactions on Artificial Intelligence, 3(6):852-866. DOI: 10.1109/TAI.2021.3133846.
Rhee, J., Park, K., Lee, S., Jang, S., and Yoon, S. (2020). Detecting hydrological droughts in ungauged areas from remotely sensed hydro-meteorological variables using rule-based models. Natural Hazards, 103(3):2961-2988. DOI: 10.1007/s11069-020-04114-5.
Ribeiro, M. T., Singh, S., and Guestrin, C. (2016). "Why should I trust you?" Explaining the predictions of any classifier. In Proceedings of the ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, volume 13-17-August-2016, pages 1135-1144. Association for Computing Machinery. DOI: 10.1145/2939672.2939778.
Rjoub, G., Bentahar, J., Abdel Wahab, O., Mizouni, R., Song, A., Cohen, R., Otrok, H., and Mourad, A. (2023). A Survey on Explainable Artificial Intelligence for Cybersecurity. IEEE Transactions on Network and Service Management, 20(4):5115-5140. DOI: 10.1109/TNSM.2023.3282740.
Sahakyan, M., Aung, Z., and Rahwan, T. (2021). Explainable Artificial Intelligence for Tabular Data: A Survey. IEEE Access, 9:135392-135422. DOI: 10.1109/ACCESS.2021.3116481.
Schapire, R. E. (1990). The strength of weak learnability. Machine learning, 5:197-227. DOI: 10.1109/SFCS.1989.63451.
Settouti, N. and Saidi, M. (2024). Preliminary analysis of explainable machine learning methods for multiple myeloma chemotherapy treatment recognition. Evolutionary Intelligence, 17(1):513 - 533. DOI: 10.1007/s12065-023-00833-3.
Shen, Y., Wu, L., and Liang, S. (2022). Explainable machine learning-based model for failure mode identification of RC flat slabs without transverse reinforcement. Engineering Failure Analysis, 141. DOI: 10.1016/j.engfailanal.2022.106647.
Shield, S. and Houston, A. (2022). Diagnosing Supercell Environments: A Machine Learning Approach. Weather and Forecasting, 37(5):771-785. DOI: 10.1175/waf-d-21-0098.1.
Shimizu, H., Enda, K., Shimizu, T., Ishida, Y., Ishizu, H., Ise, K., Tanaka, S., and Iwasaki, N. (2022). Machine Learning Algorithms: Prediction and Feature Selection for Clinical Refracture after Surgically Treated Fragility Fracture. Journal of Clinical Medicine, 11(7). DOI: 10.3390/jcm11072021.
Sokhansanj, B. and Rosen, G. (2022). Predicting Institution Outcomes for Inter Partes Review (IPR) Proceedings at the United States Patent Trial & Appeal Board by Deep Learning of Patent Owner Preliminary Response Briefs. Applied Sciences (Switzerland), 12(7). DOI: 10.3390/app12073656.
Stepin, I., Alonso, J. M., Catala, A., and Pereira-Fariña, M. (2021). A Survey of Contrastive and Counterfactual Explanation Generation Methods for Explainable Artificial Intelligence. IEEE Access, 9:11974-12001. DOI: 10.1109/ACCESS.2021.3051315.
Stojić, A., Stanić, N., Vuković, G., Stanišić, S., Perišić, M., Šoštarić, A., and Lazić, L. (2019). Explainable extreme gradient boosting tree-based prediction of toluene, ethylbenzene and xylene wet deposition. Science of the Total Environment, 653:140-147. DOI: 10.1016/j.scitotenv.2018.10.368.
Tan, S., Soloviev, M., Hooker, G., and Wells, M. T. (2020). Tree Space Prototypes: Another Look at Making Tree Ensembles Interpretable. In FODS 2020 - Proceedings of the 2020 ACM-IMS Foundations of Data Science Conference, pages 23-34. Association for Computing Machinery, Inc. DOI: 10.1145/3412815.3416893.
Tang, H., Yu, J., Lin, B., Geng, Y., Wang, Z., Chen, X., Yang, L., Lin, T., and Xiao, F. (2023). Airport terminal passenger forecast under the impact of COVID-19 outbreaks: A case study from China. Journal of Building Engineering, 65. DOI: 10.1016/j.jobe.2022.105740.
Tran, D. A., Tsujimura, M., Ha, N. T., Nguyen, V. T., Binh, D. V., Dang, T. D., Doan, Q. V., Bui, D. T., Anh Ngoc, T., Phu, L. V., Thuc, P. T. B., and Pham, T. D. (2021). Evaluating the predictive power of different machine learning algorithms for groundwater salinity prediction of multi-layer coastal aquifers in the Mekong Delta, Vietnam. Ecological Indicators, 127. DOI: 10.1016/j.ecolind.2021.107790.
Vaulet, T., Al-Memar, M., Fourie, H., Bobdiwala, S., Saso, S., Pipi, M., Stalder, C., Bennett, P., Timmerman, D., Bourne, T., and De Moor, B. (2022). Gradient boosted trees with individual explanations: An alternative to logistic regression for viability prediction in the first trimester of pregnancy. Comput. Methods Prog. Biomed., 213(C). DOI: 10.1016/j.cmpb.2021.106520.
Wang, S., Ma, C., Wang, W., Hou, X., Xiao, X., Zhang, Z., Liu, X., and Liao, J. (2023a). Prediction of Failure Modes and Minimum Characteristic Value of Transverse Reinforcement of RC Beams Based on Interpretable Machine Learning. Buildings, 13(2). DOI: 10.3390/buildings13020469.
Wang, X., Qiao, Y., Cui, Y., Ren, H., Zhao, Y., Linghu, L., Ren, J., Zhao, Z., Chen, L., and Qiu, L. (2023b). An explainable artificial intelligence framework for risk prediction of COPD in smokers. BMC Public Health, 23(1). DOI: 10.1186/s12889-023-17011-w.
Wu, H., Ruan, W., Wang, J., Zheng, D., Liu, B., Geng, Y., Chai, X., Chen, J., Li, K., Li, S., and Helal, S. (2023). Interpretable Machine Learning for COVID-19: An Empirical Study on Severity Prediction Task. IEEE Transactions on Artificial Intelligence, 4(4):764-777. DOI: 10.1109/TAI.2021.3092698.
Yasodhara, A., Asgarian, A., Huang, D., and Sobhani, P. (2021). On the Trustworthiness of Tree Ensemble Explainability Methods. In Machine Learning and Knowledge Extraction: 5th IFIP TC 5, TC 12, WG 8.4, WG 8.9, WG 12.9 International Cross-Domain Conference, CD-MAKE 2021, Virtual Event, August 17-20, 2021, Proceedings, pages 293-308, Berlin, Heidelberg. Springer-Verlag. DOI: 10.1007/978-3-030-84060-0_19.
Zhang, Y., Cheng, L., Pan, A., Hu, C., and Wu, K. (2024). Phase Transformation Temperature Prediction in Steels via Machine Learning. Materials, 17(5). DOI: 10.3390/ma17051117.
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2025 Victoria Sousa Figueira Gonçalves, Vinicius Renan de Carvalho
This work is licensed under a Creative Commons Attribution 4.0 International License.
