Accurate intelligible models with pairwise interactions
The DOI matches its Crossref record; 21 of the 22 references it cites were found in a registry or an index.
Abstract
Standard generalized additive models (GAMs) usually model the dependent variable as a sum of univariate models. Although previous studies have shown that standard GAMs can be interpreted by users, their accuracy is significantly less than more complex models that permit interactions.
Overview
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
In the citing paper
“It is designed to have high accuracy compared to the state-of-the-art machine learning models while keeping the intelligibility, and explainability [13].”
From An Empirical Comparison of Interpretable Models to Post-Hoc Explanations (2023) · cites this paper as [13]
Citations
Cites
Greedy function approximation: A gradient boosting machine
Friedman, J. H. (2001) · The Annals of Statistics · doi:10.1214/aos/1013203451 · Cited by 30,731
Generalized Additive Models: An Introduction with R
Wood, S. N. (2017) · doi:10.1201/9781315370279 · Cited by 13,852
Introduction to information retrieval
(2009) · Choice Reviews Online · doi:10.5860/choice.46-2715 · Cited by 12,278
Brown, R. A., Hastie, T. J., & Tibshirani, R. J. (1991) · Biometrics · doi:10.2307/2532174 · Cited by 8,176
An introduction to variable and feature selection
GuyonIsabelle, & ElisseeffAndré (2003) · Journal of Machine Learning Research · doi:10.5555/944919.944968 · Cited by 7,715
Koyak, R. A., Hastie, T. J., & Tibshirani, R. J. (1991) · Journal of the American Statistical Association · doi:10.2307/2290538 · Cited by 7,596
Wood, S. N. (2006) · doi:10.1201/9781420010404 · Cited by 4,953
Hastie, T., & Tibshirani, R. (2014) · Wiley StatsRef: Statistics Reference Online · doi:10.1002/9781118445112.stat03141 · Cited by 3,156
An Empirical Comparison of Voting Classification Algorithms: Bagging, Boosting, and Variants
Bauer, E., & Kohavi, R. (1999) · Machine Learning · doi:10.1023/a:1007515423169 · Cited by 2,638
Wood, S. N. (2003) · Journal of the Royal Statistical Society Series B: Statistical Methodology · doi:10.1111/1467-9868.00374 · Cited by 2,445
Research works printed but not linked: 2
- 10.5555/1394399 · doi:10.5555/1394399
- 10.5555/1622620.1622633 · doi:10.5555/1622620.1622633
Cited by
Items 201–300 of 565
Accurate and Interpretable Factorization Machines
Lan, L., & Geng, Y. (2019) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v33i01.33014139 · Cited by 17
“GAM was further extended to Generalized Additive Models Plus Interactions (GA 2 M) (Lou et al. 2013) by adding pairwise feature interactions among input features.”
MethodChen, J., Mao, X., Deng, H., Liu, Z., & Wang, Q. (2020) · Applied Geochemistry · doi:10.1016/j.apgeochem.2020.104781 · Cited by 13
Can I trust you more? Model-Agnostic Hierarchical ExplanationsPreprint
Tsang, M., Sun, Y., Ren, D., & Liu, Y. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1812.04801 · Cited by 24
“However, if we would like broader explanations, we can also obtain non-additive attributions or interactions between variables (Lou et al., 2013), which can provide an even better fit to the complex local vicinity.”
BackgroundMethodInfluentialAn Empirical Comparison of Interpretable Models to Post-Hoc Explanations
Mahya, P., & Fürnkranz, J. (2023) · AI · doi:10.3390/ai4020023 · Cited by 17
“Among various feature-based methods on interpretability, GA 2 M S [13] is selected as a glass-box model, intelligible algorithm, and MAPLE is selected as a post-hoc method.”
BackgroundMethodInfluentialAnalyzing the Differences between Professional and Amateur Esports through Win Probability
Xenopoulos, P., Freeman, W. R., & Silva, C. T. (2022) · International World Wide Web Conference (WWW) · doi:10.1145/3485447.3512277 · Cited by 20
Summarized Causal Explanations For Aggregate Views
Youngmann, B., Cafarella, M., Gilad, A., & Roy, S. (2024) · Proceedings of the ACM on Management of Data · doi:10.1145/3639328 · Cited by 15
Wahab, S., Salami, B. A., AlAteah, A. H., Al-Tholaia, M. M. H., & Alahmari, T. S. (2024) · Case Studies in Construction Materials · doi:10.1016/j.cscm.2024.e03084 · Cited by 25
Wahab, S., Khan, I. U., Khan, M. N. A., & Ashraf, M. (2024) · Construction and Building Materials · doi:10.1016/j.conbuildmat.2024.137381 · Cited by 12
An Empirical Study of Testing Machine Learning in the Wild
Openja, M., Khomh, F., Foundjem, A. T., Jiang, Z. M., Abidi, M., & Hassan, A. E. (2024) · ACM Transactions on Software Engineering and Methodology · doi:10.1145/3680463 · Cited by 24
Efficient structuring of the latent space for controllable data reconstruction and compression
Trunz, E., Weinmann, M., Merzbach, S., & Klein, R. (2022) · Graphics and Visual Computing · doi:10.1016/j.gvc.2022.200059 · Cited by 14
Wang, D., Lee, S. H., Geng, H., Zhong, H., Plastaras, J. P., Wojcieszynski, A., Caruana, R. A., & Xiao, Y. (2022) · Frontiers in Artificial Intelligence · doi:10.3389/frai.2022.1059033 · Cited by 14
“The EBM, which is a tree-based, cyclic gradient boosting generalized additive model designed to provide both intelligibility and high accuracy, has been used to find significant and unexpected impacts in healthcare data (Lou et al., 2013; Caruana et al., 2015; Lundberg and Lee, 2017).”
BackgroundSelf-citationTowards Utilitarian Online Learning -- A Review of Online Algorithms in Open Feature Space
He, Y., Schreckenberger, C., Stuckenschmidt, H., & Wu, X. (2023) · International Joint Conference on Artificial Intelligence · doi:10.24963/ijcai.2023/745 · Cited by 12
Canonico, L. B., McNeese, N. J., & Duncan, C. (2018) · Proceedings of the Human Factors and Ergonomics Society Annual Meeting · doi:10.1177/1541931218621287 · Cited by 15
“In order to resolve the interpretability question, scientists have suggested removing human input altogether and instead relying on sophisticated mathematical structures to embed interpretability within neural network (Lou et al, 2013).”
BackgroundInfluentialIncreasing Trust in (Big) Data Analytics
Schneider, J., Handali, J. P., & Brocke, J. V. (2018) · Lecture notes in business information processing · doi:10.1007/978-3-319-92898-2_6 · Cited by 13
Khattak, A., Chan, P. W., Chen, F., & Peng, H. (2023) · KSCE Journal of Civil Engineering · doi:10.1007/s12205-023-0410-8 · Cited by 13
“EBM tackles this problem by presenting a two-stage construction strategy and employing FAST (Lou et al., 2013) to rank the pair-wise interactions efficiently.”
MethodPisu, F., Chen, H., Jiang, B., Zhu, G., Usai, M. V., Austermann, M. J., Shehada, Y., Johansson, E. P., Suri, J. S., Lanzino, G. S., et al. (2023) · European Radiology · doi:10.1007/s00330-023-10347-2 · Cited by 11
Leveraging Model-Based Trees as Interpretable Surrogate Models for Model Distillation
Herbinger, J., Dandl, S., Ewald, F. K., Loibl, S., & Casalicchio, G. (2024) · Communications in computer and information science · doi:10.1007/978-3-031-50396-2_13 · Cited by 15
Explaining Local, Global, And Higher-Order Interactions In Deep Learning
Lerman, S., Venuto, C., Kautz, H., & Xu, C. (2021) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv48922.2021.00126 · Cited by 18
To predict the risk of chronic kidney disease (CKD) using Generalized Additive2 Models (GA2M)
Lapi, F., Nuti, L., Marconi, E., Medea, G., Cricelli, I., Papi, M., Gorini, M., Fiorani, M., Piccinocchi, G., & Cricelli, C. A. (2023) · Journal of the American Medical Informatics Association · doi:10.1093/jamia/ocad097 · Cited by 11
Hassani, A., Bykuć, S., Schneider, P., Zawadzki, P., Chaja, P. R., & Castell, N. (2023) · Atmospheric Environment · doi:10.1016/j.atmosenv.2023.120108 · Cited by 14
DPClass: An Effective but Concise Discriminative Patterns-Based Classification Framework
Shang, J., Tong, W., Peng, J., & Han, J. (2016) · SIAM International Conference on Data Mining · doi:10.1137/1.9781611974348.64 · Cited by 15
“Furthermore, pairwise interactions have also been introduced to improve the classification and regression [21], which is actually a two-layer trees model.”
Confidence, command, complexity: metamodels for structured interaction with machine intelligence.
Sarkar, A. (2015) · PPIG · Cited by 15
VINE: Visualizing Statistical Interactions in Black Box ModelsPreprint
Britton, M. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1904.00561 · Cited by 32
“A modified version, GA 2 M’s, adds interaction terms consisting of two features, which are again modified by a link function [34].”
BackgroundImpact of Accuracy on Model InterpretationsPreprint
Liu, B. S., & Udell, M. R. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2011.09903 · Cited by 24
“At medium levels of accuracy, EBM Local Explanations outperform XGBoost with SHAP in terms of interpretation trueness.”
MethodA Study of the Machine Learning Approach and the MGARCH-BEKK Model in Volatility Transmission
Joshi, P., Wang, J., & Busler, M. (2022) · Journal of risk and financial management · doi:10.3390/jrfm15030116 · Cited by 11
Calvo, V., Niazmand, E., Carcereny, E., Rodríguez‐Abreu, D., Cobo, M., Castro, R. L., Guirado, M., Camps, C., Granados, A. L. O., Bernabé, R., et al. (2024) · Lung Cancer · doi:10.1016/j.lungcan.2024.107920 · Cited by 12
MIRAD: A Method for Interpretable Ransomware Attack Detection
Marcinkowski, B., Goschorska, M., Wileńska, N., Siuta, J., & Kajdanowicz, T. J. (2024) · IEEE Access · doi:10.1109/access.2024.3461322 · Cited by 10
“We propose to use a solution inspired by generalized additive models (GAMs), the gold standard for interpretability [19].”
MethodInfluentialExplainable modeling for wind power forecasting: A Glass-Box model with high accuracy
Liao, W., Fang, J., Bak‐Jensen, B., Ruan, G., Yang, Z., & Porté‐Agel, F. (2025) · International Journal of Electrical Power & Energy Systems · doi:10.1016/j.ijepes.2025.110643 · Cited by 13
Bobek, S., & Nalepa, G. J. (2025) · Information Fusion · doi:10.1016/j.inffus.2025.103357 · Cited by 17
Building interpretable predictive models with context-aware evolutionary learning
Tran, B., Sudusinghe, C., Nguyen, S., & Alahakoon, D. (2022) · Applied Soft Computing · doi:10.1016/j.asoc.2022.109854 · Cited by 13
Complex Systems Modelling of UK Winter Wheat Yield
Hall, R. J., Wei, H., Pearson, S., Ma, Y., Fang, S., & Hanna, E. (2022) · Computers and Electronics in Agriculture · doi:10.1016/j.compag.2023.107855 · Cited by 13
Interpretability With Accurate Small Models
Ghose, A., & Ravindran, B. (2020) · Frontiers in Artificial Intelligence · doi:10.3389/frai.2020.00003 · Cited by 13
“…(Letham et al., 2013; Angelino et al., 2017), decision trees (Breiman et al., 1984; Quinlan, 1993, 2004), sparse linear models (Ustun and Rudin, 2016), decision sets (Lakkaraju et al., 2016), pairwise interaction models that may be linear (Lim and Hastie, 2015), or additive (Lou et al., 2013).”
BackgroundChannel Metamodeling for Explainable Data-Driven Channel Model
Lee, H.-S. (2021) · IEEE Wireless Communications Letters · doi:10.1109/lwc.2021.3111874 · Cited by 10
Ntekouli, M., Spanakis, G., Waldorp, L., & Roefs, A. (2022) · Lecture notes in computer science · doi:10.1007/978-3-031-01333-1_16 · Cited by 9
Perspectives on incorporating expert feedback into model updates
Chen, V., Bhatt, U., Heidari, H., Weller, A., & Talwalkar, A. (2023) · Patterns · doi:10.1016/j.patter.2023.100780 · Cited by 20
“Active data collection Adding data [16, 45, 51, 121] Relabeling data [76] Reweighting data [12, 64, 137] Collecting expert labels [98] Passive observation [69, 84, 118] Constraint elicitation Metric learning [22, 62, 72, 131] Human representations [60, 110] Collecting contextual information Generative factors [3] Conc…”
MethodUsing Explainable Boosting Machines (EBMs) to Detect Common Flaws in Data
Chen, Z., Tan, S., Nori, H., Inkpen, K. M., Lou, Y., & Caruana, R. (2021) · Communications in computer and information science · doi:10.1007/978-3-030-93736-2_40 · Cited by 19
Self-citationImangaliyev, S., Schlötterer, J., Meyer, F., & Seifert, C. (2022) · Diagnostics · doi:10.3390/diagnostics12102514 · Cited by 10
“To understand how the model makes its predictions and consequently increase trust in the model, Explainable (also sometimes interchangeably called Intelligible or Interpretable) machine learning models [24] should be used in biomedical applications involving microbiome data.”
BackgroundCapturing the form of feature interactions in black-box models
Zhang, H., Zhang, X., Zhang, T., & Zhu, J. (2023) · Information Processing & Management · doi:10.1016/j.ipm.2023.103373 · Cited by 12
Non-monotonic relations of galaxy star formation, radius, and structure at fixed stellar mass
Stephenson, J., Rodríguez-Puebla, A., Faber, S. M., Primack, J. R., Ávila-Reese, V., Calette, A. R., Cannarozzo, C., Kakos, J., Cano-Díaz, M., Koo, D. C., et al. (2024) · Monthly Notices of the Royal Astronomical Society · doi:10.1093/mnras/stae1735 · Cited by 13
Visual instance-based recommendation system for medical data mining
Falip, J., Younes, A. A., Blanchard, F., Delemer, B., Diallo, A., & Herbin, M. (2017) · Procedia Computer Science · doi:10.1016/j.procs.2017.08.205 · Cited by 9
Guo, M., Xu, Z., Zhang, Q., Liao, X., & Liu, J. (2021) · ACM Transactions on Knowledge Discovery from Data · doi:10.1145/3487048 · Cited by 9
“[ 20, 21] used shape functions to measure the main effects and mapped the interaction effects to real values.”
BackgroundMethodInfluentialExplainable Failure Predictions with RNN Classifiers based on Time Series DataPreprint
Giurgiu, I., & Schumann, A. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1901.08554 · Cited by 16
“Typical examples include decision trees, decision sets (Lakkaraju, Bach, and Leskovec 2016; Ribeiro, Singh, and Guestrin 2018), fuzzy inference models (Lou et al. 2013) or additive models (Poulin et al. 2006).”
BackgroundData-driven discovery of interpretable water retention models for deformable porous media
Suh, H. S., Song, J. Y., Kim, Y., Yu, X. B., & Choo, J. (2024) · Acta Geotechnica · doi:10.1007/s11440-024-02322-y · Cited by 9
“Although there have been several attempts to address this issue of non-interpretability (e.g., [3, 45, 63]), the lack of an analytical expression makes them only partially interpretable while being less accurate than their black-box counterparts.”
Zhang, W., Zhang, X., Chen, J., Li, J., & Ma, Z. (2024) · International Journal of General Systems · doi:10.1080/03081079.2024.2384404 · Cited by 8
“Ultimately, we derive the GA 2 M model (Generalized Additive Model plus Interactions) on both the individual features and interaction terms F t ( x ( t ) ) = (cid”
InfluentialErduran, H., Esener, N., Keskin, İ., & Dağ, B. (2024) · Tropical Animal Health and Production · doi:10.1007/s11250-024-04145-1 · Cited by 8
“Multicol-linearity is not the main issue for the other models employed in this study as they are known to rely on the independent contribution of each predictor variable (Bruce et al. 2020; Lou et al. 2013).”
Beaugrand, G. (2024) · Ecosphere · doi:10.1002/ecs2.70015 · Cited by 10
StratoMod: predicting sequencing and variant calling errors with interpretable machine learning
Dwarshuis, N. J., Tonner, P. D., Olson, N. D., Sedlazeck, F. J., Wagner, J., & Zook, J. M. (2024) · Communications Biology · doi:10.1038/s42003-024-06981-1 · Cited by 9
“To this end, we chose Explainable Boosting Machines (EBMs) 21 , which are a speci fi c imple-mentationofgeneralizedadditivemodels(GAMs)wheremodelpredictions arederivedfromadditiveeffectsofunivariateandpairwisefunctionsof datasetfeatures(see “ Methods ” section for equation form).”
Automation of quantum dot measurement analysis via explainable machine learning
Schug, D., Kovach, T. J., Wolfe, M. A., Benson, J. H., Park, S., Dodson, J. P., Corrigan, J. D., Eriksson, M. A., & Zwolak, J. P. (2025) · Machine Learning Science and Technology · doi:10.1088/2632-2153/ada087 · Cited by 16
“In contrast with many black-box ML models, explainable boosting machines (EBMs) are a glass-box method that enables the model to be directly interpretable rather than relying on surrogate explanations [10].”
Gao, Y., Zhang, Z., & Yu, W. (2025) · Information Fusion · doi:10.1016/j.inffus.2025.103443 · Cited by 8
Structure, Interactions, and Assembly of Membrane-Active Antimicrobial Polypeptides
Lee, T.-H., Charchar, P., Sani, M., Le, D.-H., Le, T. C., Yarovsky, I., Separovic, F., & Aguilar, M. (2026) · Chemical Reviews · doi:10.1021/acs.chemrev.5c00994 · Cited by 13
Nilofer, A., & Sasikala, S. (2023) · Computing Open · doi:10.1142/s2972370123500034 · Cited by 12
ILMART: Interpretable Ranking with Constrained LambdaMART
Lucchese, C., Nardini, F. M., Orlando, S., Perego, R., & Veneri, A. (2022) · International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR) · doi:10.1145/3477495.3531840 · Cited by 17
“• EBM, an efficient implementation ofGA2M using amixed baggingboosting procedure [9].”
MethodInfluentialImproving medical experts’ efficiency of misinformation detection: an exploratory study
Nabożny, A., Balcerzak, B., Morzy, M., Wierzbicki, A., Savov, P., & Warpechowski, K. (2022) · World Wide Web · doi:10.1007/s11280-022-01084-5 · Cited by 13
“The most popular approaches include decision tree-based explainers [15], using Boolean rules to identify target classes [7], and Explainable Boosting Machines [23].”
MethodInteractive Generalized Additive Model and Its Applications in Electric Load Forecasting
Yang, L., Ren, R., Gu, X., & Sun, L. (2023) · ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD) · doi:10.1145/3580305.3599848 · Cited by 15
“as GA M [33], FLAM [41].”
Santos, J. I., Martín, Ó., Ahedo, V., Tiedra, P. D., & Galán, J. M. (2022) · The International Journal of Advanced Manufacturing Technology · doi:10.1007/s00170-022-10444-4 · Cited by 9
“Specifically, it uses an efficient algorithm, called FAST [46], to establish a ranking of the strength of the interactions; from the ranking, a greedy forward selection strategy is used until convergence, being selected in the model only those interactions that are relevant for prediction.”
MethodTaieb, S. B., Huser, R., Hyndman, R. J., & Genton, M. G. (2022) · RePEc: Research Papers in Economics · doi:10.26180/21521286 · Cited by 9
Technologies for Trustworthy Machine Learning: A Survey in a Socio-Technical ContextPreprint
Toreini, E., Aitken, M., Coopamootoo, K., Elliott, K., González-Zelaya, V., Missier, P., Ng, M., & van Moorsel, A. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2007.08911 · Cited by 33
“[141], is one of the more well–known transparent models.”
BackgroundComments on: A random forest guided tour
Hooker, G., & Mentch, L. (2016) · Test · doi:10.1007/s11749-016-0485-3 · Cited by 7
“Such models can be fit using boosting methods (see Fahrmeir et al. 2013, for parametric models) or via backfitting schemes (Sorokina et al. 2007; Lou et al. 2013).”
Self-citationAmekoe, K. M., Azzag, H., Dagdia, Z. C., Lebbah, M., & Jaffre, G. (2024) · Neural Computing and Applications · doi:10.1007/s00521-024-10163-9 · Cited by 8
“To solve the problem of effect identification when adding pairwise interactions, additional heredity constraints [29] or interaction purification [30] is used.”
Nasir, M., Summerfield, N. S., Simsek, S., & Oztekin, A. (2024) · Decision Sciences · doi:10.1111/deci.12642 · Cited by 8
Cunha, B. M., & Barbosa, S. D. J. (2024) · Brazilian Symposium on Human Factors in Computing Systems (IHC) · doi:10.1145/3702038.3702093 · Cited by 20
“Biran and Cotton [4], Mit-telstadt et al. [22], and Lou et al. [18] understand an interpretable model to be one of which a person can have an understanding of its inner mechanisms.”
InfluentialExplainable time-to-progression predictions in multiple sclerosis
D’hondt, R., Dedja, K., Aerts, S., Wijmeersch, B. V., Kalinčík, T., Reddel, S., Havrdová, E., Lugaresi, A., Weinstock‐Guttman, B., Mrabet, S., et al. (2025) · Computer Methods and Programs in Biomedicine · doi:10.1016/j.cmpb.2025.108624 · Cited by 9
Insights into heart failure metabolite markers through explainable machine learning
Baron, C., Mehanna, P., Daneault, C., Hausermann, L., Busseuil, D., Tardif, J., Dupuis, J., Rosiers, C. D., Ruiz, M., & Hussin, J. (2025) · Computational and Structural Biotechnology Journal · doi:10.1016/j.csbj.2025.02.041 · Cited by 9
Sparse-enhanced additive interaction neural network for interpretable credit decision
Lan, X., Fan, H., Liu, W., Xia, M., & Guo, K. (2025) · Decision Support Systems · doi:10.1016/j.dss.2025.114507 · Cited by 9
Kang, W., Li, B., Jiskoot, L. C., Deyn, P. P. D., Biessels, G. J., Koek, H. L., Claassen, J. A. H. R., Middelkoop, H. A. M., van der Flier, W. M., Jansen, W. J., et al. (2026) · Computerized Medical Imaging and Graphics · doi:10.1016/j.compmedimag.2026.102722 · Cited by 8
Qureshi, M. A., Noor, A. A., Manzoor, A., Mazhar Qureshi, M. D., Younus, A., & Rashwan, W. (2026) · PLOS One · doi:10.1371/journal.pone.0351473 · Cited by 7
“Ante-hoc methods are inherently interpretable by design; examples include EBM (a GA 2 M with learned interactions) and TabNet (an attentive neural architecture with per-sample feature selection) [18,19].”
Zeitlin, J. H., Fontana, M. A., Parides, M. K., Nawabi, D. H., Wickiewicz, T. L., Pearle, A. D., Beynnon, B. D., & Imhauser, C. W. (2023) · Orthopaedic Journal of Sports Medicine · doi:10.1177/23259671231163627 · Cited by 8
An Explainable Feature Selection Approach for Fair Machine Learning
Yang, Z., Wang, Z., Huang, C., & Yao, X. (2023) · Lecture notes in computer science · doi:10.1007/978-3-031-44198-1_7 · Cited by 10
Kang, W., Li, B., Papma, J. M., Jiskoot, L. C., Deyn, P. P. D., Biessels, G. J., Claassen, J. A. H. R., Middelkoop, H. A. M., van der Flier, W. M., Ramakers, I. H. G. B., et al. (2023) · Lecture notes in computer science · doi:10.1007/978-3-031-47401-9_7 · Cited by 15
Enhanced ML-Based Approach for Functional Safety Improvement in Automotive AMS Circuits
Arunachalam, A., Das, S., Rajan, M., Su, F., Jin, X. R., Banerjee, S., Raha, A., Natarajan, S., & Basu, K. (2023) · IEEE International Test Conference (ITC) · doi:10.1109/itc51656.2023.00043 · Cited by 8
“3) Explainable Boosting Machine: EBM is a tree-based Generalized Additive Model (GAM), which furnishes high detection performance in addition to retaining the interpretability of its predictions [5], [27].”
BackgroundFXAM: A Unified and Fast Interpretable Model for Predictive Analytics
Jiang, Y., Ding, R., Qiao, T., Zhu, Y., Han, S., & Zhang, D. (2023) · Expert Systems with Applications · doi:10.1016/j.eswa.2024.123890 · Cited by 10
Liu, B. S., Xie, M., & Udell, M. R. (2021) · ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD) · doi:10.1145/3447548.3467387 · Cited by 9
“Explainable boosting machines are generalized additive models composed of boosted trees trained on a single feature [19].”
BackgroundBridging Breiman's Brook: From Algorithmic Modeling to Statistical Learning
Hooker, G., & Mentch, L. (2021) · Observational Studies · doi:10.1353/obs.2021.0027 · Cited by 15
Self-citationShrivastava, H., & Chajewska, U. (2023) · Lecture notes in computer science · doi:10.1007/978-3-031-45608-4_22 · Cited by 16
Comprehensible Models for Reconfiguring Enterprise Relational Databases to Avoid Incidents
Giurgiu, I., Botezatu, M. M., & Wiesmann, D. (2015) · ACM International Conference on Information and Knowledge Management (CIKM) · doi:10.1145/2806416.2806448 · Cited by 9
“Keeping the need for performance in mind, we use the FAST algorithm [18] for quick pairwise interaction detection.”
BackgroundMethodImproving Competence for Reliable Autonomy
Basich, C., Svegliato, J., Wray, K. H., Witwicki, S. J., & Zilberstein, S. (2020) · Electronic Proceedings in Theoretical Computer Science · doi:10.4204/eptcs.319.4 · Cited by 8
“We implement our feedback profile λ as a GA2M [23].”
MethodGoverning Transport in the Algorithmic Age
Forum, I. T. (2019) · International transport forum policy papers · doi:10.1787/eec0b9aa-en · Cited by 10
Khalili, H., Frey, H., & Wimmer, M. A. (2025) · Future Internet · doi:10.3390/fi17040155 · Cited by 7
Explainable gradient boosting for corporate crisis forecasting in Italian businesses
Maturo, F., Riccio, D., Mazzitelli, A., Bifulco, G. M., & Paolone, F. (2025) · Annals of Operations Research · doi:10.1007/s10479-025-06570-3 · Cited by 9
“The training procedure for EBM involves using the GA 2 M algorithm (Lou et al., 2013, 2012;Caruanaetal.,2015),whichemploysacombinationofbaggingandgradientboostingto learnthemaineffectfunctionsandautomaticallydetectspairwiseinteractions.”
InfluentialExplainable for Trustworthy AI
Giannotti, F., Naretto, F., & Bodria, F. (2023) · Lecture notes in computer science · doi:10.1007/978-3-031-24349-3_10 · Cited by 9
Benchmarking alternative interpretable machine learning models for corporate probability of default
Jacobs, M. R., & Ph.D, C. (2024) · Data Science in Finance and Economics · doi:10.3934/dsfe.2024001 · Cited by 10
On marginal feature attributions of tree-based models
Filom, K., Miroshnikov, A., Kotsiopoulos, K., & Kannan, A. R. (2024) · Foundations of Data Science · doi:10.3934/fods.2024021 · Cited by 12
“Explainable Boosting Machines [43] are based on Generalized Additive Models plus Interactions [34].”
A Two-Stage ECG Classifier for Decentralized Inferencing Across Edge-Cloud Continuum
Li, X., Cardiff, B., & John, D. (2024) · IEEE Sensors Journal · doi:10.1109/jsen.2024.3406780 · Cited by 8
“EBM is a tree-based, cyclic gradient boosting generalized additive model (GAM) with automatic interaction detection [42].”
MethodInterpretability in the modeling spectrum: A conceptual framework and a quantification index
Aguirre-Zapata, E., Álvarez, H., Lema-Pérez, L., di Sciascio, F. A., & Amicarelli, A. (2024) · Ecological Modelling · doi:10.1016/j.ecolmodel.2024.110882 · Cited by 6
Explainable AI for tool condition monitoring using Explainable Boosting Machine
Colantonio, L., Equeter, L., Dehombreux, P., & Ducobu, F. (2025) · Procedia CIRP · doi:10.1016/j.procir.2025.02.025 · Cited by 6
TimberSleuth: Visual anomaly detection with human feedback for mitigating the illegal timber trade
Datta, D., Self, N., Simeone, J., Meadows, A., Outhwaite, W., Walker, L., Elmqvist, N., & Ramakrishnan, N. (2023) · Information Visualization · doi:10.1177/14738716231157081 · Cited by 9
“Generalized linear and additive models such as factorization machines 52 and GA 2 M 53 have been proposed for classification and ranking tasks on large scale data.”
MethodFLAN: feature-wise latent additive neural models for biological applications
Nguyen, A.-P., Vasilaki, S., & Martínez, M. R. (2023) · Briefings in Bioinformatics · doi:10.1093/bib/bbad056 · Cited by 8
Marzouk, M., Zitoun, C., Belghith, O., & Skhiri, S. (2023) · IEEE Intelligent Systems · doi:10.1109/mis.2023.3320438 · Cited by 10
“11 Although it provides a nice abstraction model on top of explainability models, it still has limitations.”
BackgroundKhattak, A., Zhang, J., Chan, P. W., Chen, F., & Almujibah, H. R. (2023) · Atmosphere · doi:10.3390/atmos15010020 · Cited by 10
“…of a two-stage construction The challenge is addressed by EBM through the implementation of a two-stage construction strategy and the utilization of FAST [37] to effectively rank the pairwise interactions. strategy and the utilization of FAST [37] to e ff ectively rank the pairwise interactions.”
MethodInterpretable Machine Learning Based on Functional ANOVA Framework: Algorithms and Comparisons
Hu, L., Nair, V. N., Sudjianto, A., Zhang, A., Chen, J., & Yang, Z. (2025) · Applied Stochastic Models in Business and Industry · doi:10.1002/asmb.2916 · Cited by 12
Constrained Generalized Additive 2 Model With Consideration of High-Order Interactions
Watanabe, A., Kuramata, M., Majima, K., Kiyohara, H., Kondo, K., & Nakata, K. (2021) · International Conference on Electrical, Computer and Energy Technologies (ICECET) · doi:10.1109/icecet52533.2021.9698779 · Cited by 9
Deep Learning Image Recognition for Non-images
Kovalerchuk, B., Kalla, D. C., & Agarwal, B. (2022) · Studies in computational intelligence · doi:10.1007/978-3-030-93119-3_3 · Cited by 6
Mixture of Linear Models Co-supervised by Deep Neural Networks
Seo, B., Lin, L., & Li, J. (2022) · Journal of Computational and Graphical Statistics · doi:10.1080/10618600.2022.2107533 · Cited by 10
“More recently, Guo et al. (2020) have used neural networks to efficiently learn the classic GAM (Hastie and Tibshirani, 1990) models.”
MethodInfluentialEmpowering Adaptive Human Autonomy Collaboration with Artificial Intelligence
Alix, C., Lafond, D., Mattioli, J., de Heer, J., Chattington, M., & Robic, P. (2021) · International Conference on System of Systems Engineering · doi:10.1109/sose52739.2021.9497497 · Cited by 13
Graham-Knight, J. B., Bond, C., Najjaran, H., Lucet, Y., & Lasserre, P. (2022) · Expert Systems with Applications · doi:10.1016/j.eswa.2022.119101 · Cited by 6
Temperature Prediction in Blast Furnaces: A Machine Learning Comparative Study
Navarro, L. C., Amorim, L. L., Berriel, R. F., Paixão, T. M., Rampinelli, V. T. L., Wasem, L. A., Quaresma, L., Badue, C. S., Souza, A. F. D., & Oliveira-Santos, T. (2022) · SIBGRAPI Conference on Graphics, Patterns and Images (SIBGRAPI) · doi:10.1109/sibgrapi55357.2022.9991787 · Cited by 6
“…to SVM and MLP, largely used in problems related to ours, the system was tested with the following algorithms, which are also popular in the literature: Extreme Gradient Boosting (XGBoost) [17], Light Gradient Boosting Machine [18], Explainable Boosting Machine (EBM) [19], and Random Forest (RF).”
MethodExplanation-Based Tuning of Opaque Machine Learners with Application to Paper RecommendationPreprint
Lee, B. C. G., Lo, K., Downey, D., & Weld, D. S. (2020) · arXiv (Cornell University) · Cited by 6
Towards Rigorous Interpretations: a Formalisation of Feature AttributionPreprint
Afchar, D., Hennequin, R., & Guigue, V. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2104.12437 · Cited by 12
“…is to consider only summed univariate contributions – e.g. GAM (Hastie and Tibshirani, 1990); or interactions up to a fixed order – e.g. GA 2 M (Lou et al., 2013), NIT (Tsang et al., 2018); or with a fixed structure – e.g. Archipelago (Tsang et al., 2020), InterpretableNN (Afchar and Hennequin,…”
BackgroundTargeting resources efficiently and justifiably by combining causal machine learning and theory
Ali, Ö. G. (2022) · Frontiers in Artificial Intelligence · doi:10.3389/frai.2022.1015604 · Cited by 8
“Generalized additive models plus interactions (GA2M) extend this work with the FAST algorithm to include two-way interaction terms ranked based on importance, which is particularly useful for high-dimensional datasets (Lou et al., 2013).”
MethodDevarajan, H. R. (2024) · Journal of Propulsion Technology · doi:10.52783/tjjpt.v45.i02.6376 · Cited by 6
“…image classification, where it can highlight the image regions most influential to the model's decision; natural language processing, where it can identify key words or phrases affecting the output; and recommendation systems, [5],[6] where it can reveal the features driving the recommended items.”
Background
Metadata
- Authors
- Lou, Y., Caruana, R., Gehrke, J., & Hooker, G.
- Affiliations
- Cornell University (US)
- Microsoft (United States) (US)
- Venue
- Proceedings of the 19th ACM SIGKDD international conference on Knowledge discovery and data mining
- Publisher
- ACM
- Published
- 2013-08-11
- Pages
- 623-631
- OpenAlex
- W2046945713
- Cited by
- 564
- References
- 22
- Citations by year
- 2026: 66 · 2025: 78 · 2024: 88 · 2023: 87 · 2022: 65 · 2021: 57 · 2020: 45 · 2019: 29 · 2018: 24 · 2017: 11 · 2016: 8 · 2015: 4 · 2014: 2
- FWCI
- 3.01
- Type
- conference paper
- Language
- en
- Open access
- closed
- Locations
- ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD) (publishedVersion)
- Topics
- Physical Sciences › Computer Science › Artificial Intelligence › Explainable Artificial Intelligence (XAI)
- Physical Sciences › Mathematics › Statistics and Probability › Statistical Methods and Applications
- Physical Sciences › Computer Science › Computer Graphics and Computer-Aided Design › Data Visualization and Analytics
- Keywords
- generalized additive models, pairwise interactions, model interpretability, model accuracy
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.