The DOI matches its Crossref record; 35 of the 36 references it cites were found in a registry or an index.
Predictive learning via rule ensembles
Open accessAbstract
General regression and classification models are constructed as linear combinations of simple rules derived from the data. Each rule consists of a conjunction of a small number of simple statements concerning the values of individual input variables. These rule ensembles are shown to produce predictive accuracy comparable to the best methods. However, their principal advantage lies in interpretation. Because of its simple form, each rule is easy to understand, as is its influence on individual predictions, selected subsets of predictions, or globally over the entire space of joint input variable values. Similarly, the degree of relevance of the respective input variables can be assessed globally, locally in different regions of the input space, or at individual prediction points. Techniques are presented for automatically identifying those variables that are involved in interactions with other variables, the strength and degree of those interactions, as well as the identities of the other variables with which they interact. Graphical representations are used to visualize both main and interaction effects.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
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?
The source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“To overcome the black-box nature of GBM, (Breiman 2001; Friedman and Popescu 2008; Hastie et al. 2009) introduced two important tools to interpret the GBM model: (i) variable importance measures and (ii) partial dependence plots.”
From Modelling Motor Insurance Claim Frequency and Severity Using Gradient Boosting (2023) · cites this paper as Friedman and Popescu 2008
Experimental — accuracy not yet measuredThe source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“DT are the replica of if-then rules and a number of works like RuleFit [43] which employs DT have proved capable of understanding the sparse relation between the variables which is quite difficult to understand by regression models.”
From A Review of Trustworthy and Explainable Artificial Intelligence (XAI) (2023) · cites this paper as [43]
Experimental — accuracy not yet measured
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
Breiman, L. (2001) · Machine Learning · doi:10.1023/a:1010933404324 · Cited by 133,538 · cited 5×
“The ensemble based only on rules provides somewhat improved performance by being better able to approximate the nonlinearity while crudely approximating the linear dependence by piecewise constants.”
BackgroundMethodInfluentialRegression shrinkage and selection via the lasso
Tibshirani, R. (1996) · Journal of the Royal Statistical Society Series B: Statistical Methodology · doi:10.1111/j.2517-6161.1996.tb02080.x · Cited by 51,482 · cited 1×
“M 1 , often with many being set to zero [see Tibshirani (1996), Donoho et al. (1995)].”
BackgroundAn Introduction to the Bootstrap
Efron, B., & Tibshirani, R. J. (1994) · doi:10.1201/9780429246593 · Cited by 40,500
Greedy function approximation: A gradient boosting machine
Friedman, J. H. (2001) · The Annals of Statistics · doi:10.1214/aos/1013203451 · Cited by 30,731 · cited 8×
“For binary classification y ∈ {− 1 , 1 } , a variety of loss criteria have been proposed [see Hastie, Tibshirani and Friedman (2001)].”
BackgroundMethodInfluentialSelf-citationThe Elements of Statistical Learning
Hastie, T., Friedman, J., & Tibshirani, R. (2001) · Springer Series in Statistics · doi:10.1007/978-0-387-21606-5 · Cited by 24,162
Self-citationClassification and Regression Trees.
Gordon, A. D., Breiman, L., Friedman, J. H., Olshen, R. A., & Stone, C. J. (1984) · Biometrics · doi:10.2307/2530946 · Cited by 23,522
Self-citation(1992) · Cited by 23,431
An Introduction to the Bootstrap
Efron, B., & Tibshirani, R. J. (1993) · doi:10.1007/978-1-4899-4541-9 · Cited by 21,230
Classification and Regression Trees.
Ryzin, J. V., Breiman, L., Friedman, J. H., Olshen, R. A., & Stone, C. J. (1986) · Journal of the American Statistical Association · doi:10.2307/2288003 · Cited by 20,825
Self-citationBreiman, L. (1996) · Machine Learning · doi:10.1007/bf00058655 · Cited by 16,325 · cited 4×
“An approximation F(x) to F∗(x) is derived by applying a learning procedure to these data. 2. Ensemble learning. Learning ensembles have emerged as being among the most powerful learning methods [see Breiman (1996, 2001), Freund and Schapire (1996), Friedman (2001)]. Their structural model takes the form F(x)=a 0 + XM…”
MethodInfluentialBrown, R. A., Hastie, T. J., & Tibshirani, R. J. (1991) · Biometrics · doi:10.2307/2532174 · Cited by 8,176
Robust estimation of a location parameter
Huber, P. J. (1964) · The Annals of Mathematical Statistics · doi:10.1214/aoms/1177703732 · Cited by 7,228
Cohen, W. W. (1995) · Machine Learning Proceedings 1995 · doi:10.1016/b978-1-55860-377-6.50023-2 · Cited by 3,787
Hastie, T., & Tibshirani, R. (2014) · Wiley StatsRef: Statistics Reference Online · doi:10.1002/9781118445112.stat03141 · Cited by 3,156
Clark, P., & Niblett, T. (1989) · Machine Learning · doi:10.1007/bf00116835 · Cited by 2,267 · cited 1×
“Actual ILP algorithms such as CN2 [Clark and Niblett (1989)], RIPPER [Cohen (1995)], and PRO-GOL [Muggleton (1995)] differ with respect to the detailed techniques that implement the generic paradigm.”
MethodHedonic housing prices and the demand for clean air
Harrison, D., & Rubinfeld, D. L. (1978) · Journal of Environmental Economics and Management · doi:10.1016/0095-0696(78)90006-2 · Cited by 1,854
Wavelet Shrinkage: Asymptopia?
Donoho, D. L., Johnstone, I. M., Kerkyacharian, G., & Picard, D. (1995) · Journal of the Royal Statistical Society Series B: Statistical Methodology · doi:10.1111/j.2517-6161.1995.tb02032.x · Cited by 1,749 · cited 1×
“M 1 , often with many being set to zero [see Tibshirani (1996), Donoho et al. (1995)].”
BackgroundMuggleton, S. (1995) · New Generation Computing · doi:10.1007/bf03037227 · Cited by 1,411 · cited 1×
“Actual ILP algorithms such as CN2 [Clark and Niblett (1989)], RIPPER [Cohen (1995)], and PRO-GOL [Muggleton (1995)] differ with respect to the detailed techniques that implement the generic paradigm.”
MethodInductive Logic Programming: Techniques and Applications
Lavrač, N., & Džeroski, S. (1993) · Cited by 760
Ruczinski, I., Kooperberg, C., & LeBlanc, M. (2003) · Journal of Computational and Graphical Statistics · doi:10.1198/1061860032238 · Cited by 271 · cited 1×
“Designed for problems involving binary valued features, logic regression [Ruczinski, Kooperberg and LeBlanc (2003)] uses regression to fit the coef-ficients of a model that is additive in rules “logic trees.””
MethodOn bagging and nonlinear estimation
Friedman, J. H., & Hall, P. (2007) · Journal of Statistical Planning and Inference · doi:10.1016/j.jspi.2006.06.002 · Cited by 183 · cited 1×
“A “bagged” ensemble [Breiman (1996)] is obtained by using squared-error loss, L ( y, ˆ y ) = ( y − ˆ y ) 2 , and setting ν = 0, and η = N/ 2 or, equivalently, choosing S m (line 3) to be a bootstrap sample [Friedman and Hall (2007)].”
MethodSelf-citationAn overtraining-resistant stochastic modeling method for pattern recognition
Kleinberg, E. M. (1996) · The Annals of Statistics · doi:10.1214/aos/1032181157 · Cited by 145 · cited 2×
“Details are presented in Ho and Kleinberg (1996) and Kleinberg (2000).”
BackgroundOn the algorithmic implementation of stochastic discrimination
Kleinberg, E. M. (2000) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/34.857004 · Cited by 138 · cited 1×
“Details are presented in Ho and Kleinberg (1996) and Kleinberg (2000).”
BackgroundTHE DIMENSION DISTRIBUTION AND QUADRATURE TEST FUNCTIONS
Owen, A. B. (2003) · Cited by 123
Importance Sampled Learning Ensembles
Friedman, J. H., & Popescu, B. E. (2003) · Cited by 111
Self-citationBuilding projectable classifiers of arbitrary complexity
Ho, T. K., & Kleinberg, E. M. (1996) · Proceedings - International Conference on Pattern Recognition/Proceedings/International Conference on Pattern Recognition · doi:10.1109/icpr.1996.547202 · Cited by 94 · cited 3×
“Details are presented in Ho and Kleinberg (1996) and Kleinberg (2000).”
BackgroundGradient Directed Regularization for Linear Regression and Classi…cation
FriedmanBogdan, J. H., & Popescu, E. (2004) · Cited by 86
An, J., & Owen, A. B. (2001) · Journal of Complexity · doi:10.1006/jcom.2001.0588 · Cited by 85
Weiss, S. M., & Indurkhya, N. (2000) · Cited by 68
KDD-cup 99: knowledge discovery in a charitable organization's donor database
Rosset, S., & Inger, A. (2000) · ACM SIGKDD Explorations Newsletter · doi:10.1145/846183.846204 · Cited by 45 · cited 1×
“Closer to the approach presented here is that of Rosset and Inger (2000).”
MethodA statistical approach to rule learning
Rückert, U., & Krämer, S. (2006) · International Conference on Machine Learning · doi:10.1145/1143844.1143943 · Cited by 24 · cited 1×
“Ruckert and Kramer (2006) propose the use of regularized regression to construct weighted rule ensembles for classification.”
BackgroundPfahringer, B., Holmes, G., & Wang, C. (2004) · Research Commons (University of Waikato) · Cited by 14
The ecological approach to learning
Kruse, J. M., & Reed, E. S. (1981) · Behavioral and Brain Sciences · doi:10.1017/s0140525x00008086 · Cited by 12
Visualization and exploration of high-dimensional functions using the functional anova decomposition
Roosen, C. B. (1996) · Cited by 11
(1996)
Research works printed but not linked: 2
- Cohen, W. and Singer, Y. (1999). A simple, fast and efficient rule learner. In Proceedings of the Sixteenth National Conference on Artificial Intelligence (AAAI–99) 335–342. AAAI Press.
- Mitchell, T. (1997). Machine Learning. McGraw-Hill, New York.
Cited by
Interpreting Black-Box Models: A Review on Explainable Artificial Intelligence
Hassija, V., Chamola, V., Mahapatra, A., Singal, A., Goel, D., Huang, K., Scardapane, S., Spinelli, I., Mahmud, M., & Hussain, A. (2024) · Cognitive Computation · doi:10.1007/s12559-023-10179-8 · Cited by 2,495
“Freidman established the H-statistic and discovered a mechanism to gauge the strength of feature interaction [106].”
BackgroundTMVA - Toolkit for Multivariate Data Analysis
Höcker, A., Speckmayer, P., Stelzer, J., Therhaag, J., von Toerne, E., Voss, H., Backes, M., Carli, T., Cohen, O., Christov, A., et al. (2007) · arXiv (Cornell University) · doi:10.48550/arxiv.physics/0703039 · Cited by 781
“h variables ) of the neural network has not been specified. 5.8 Predictive learning via rule ensembles (RuleFit) This classifier is a TMVAimplementation of Friedman-Popscus’ RuleFit method described in [19]. Its idea is to use an ensemble of so-calledrules to create a scoring function with good classification power. Each…”
MethodInfluentialDefinitions, methods, and applications in interpretable machine learning
Murdoch, W. J., Singh, C., Kumbier, K., Abbasi-Asl, R., & Yu, B. (2019) · Proceedings of the National Academy of Sciences · doi:10.1073/pnas.1900654116 · Cited by 2,167
“rules (38, 39), which can easily be simulated.”
BackgroundMachine Learning Interpretability: A Survey on Methods and Metrics
Carvalho, D. V., Pereira, E. M., & Cardoso, J. S. (2019) · Electronics · doi:10.3390/electronics8080832 · Cited by 1,842
“Partial Dependence Plot [142] Global Feature summary Individual Condition Expectation [143] Global/Local Feature summary Accumulated Local Effects Plot [144] Global Feature summary Feature Interaction [145] Global Feature summary Feature Importance [146] Global/Local Feature summary Local Surrogate Model [98] Local Su…”
BackgroundBig Data: New Tricks for Econometrics
Varian, H. R. (2014) · Journal of Economic Perspectives · doi:10.1257/jep.28.2.3 · Cited by 1,557
Metadata
- Authors
- Friedman, J. H., & Popescu, B. E.
- Affiliations
- Stanford University (US)
- ORCID
- Friedman, Jerome H.
- Venue
- The Annals of Applied Statistics
- Publisher
- Institute of Mathematical Statistics
- Published
- 2008-09-01
- Volume
- 2
- Issue
- 3
- Pages
- 916-954
- ISSN
- 1932-6157 (ISSN-L)
- 1941-7330
- OpenAlex
- W2048231652
- Cited by
- 1,315
- References
- 36
- Citations by year
- 2026: 151 · 2025: 187 · 2024: 114 · 2023: 128 · 2022: 121 · 2021: 159 · 2020: 88 · 2019: 54 · 2018: 40 · 2017: 33 · 2016: 21 · 2015: 22 · 2014: 26 · 2013: 31 · 2012: 28
- FWCI
- 50.74
- Type
- journal article
- Language
- en
- Open access
- bronze
- doi.org
- Locations
- The Annals of Applied Statistics (publishedVersion)
- arXiv (Cornell University) (submittedVersion)
- Project Euclid (Cornell University) (submittedVersion)
- arXiv (Cornell University)
- Funders
- National Science Foundation (DE-AC02-76SF00515, DMS-97-64431)
- U.S. Department of Energy (76SF00515, DE–AC02–76SF00515, AC02‐76SF00515, DE-AC02-)
- Topics
- Physical Sciences › Computer Science › Artificial Intelligence › Explainable Artificial Intelligence (XAI)
- Physical Sciences › Computer Science › Information Systems › Data Mining Algorithms and Applications
- Physical Sciences › Mathematics › Statistics and Probability › Statistical Methods and Applications
- Keywords
- rule ensembles, rule-based classification, interpretability, input space partitioning, model interpretability
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.