2008
DOI: 10.1109/tkde.2007.190734
|View full text |Cite
|
Sign up to set email alerts
|

Explaining Classifications For Individual Instances

Abstract: We present a method for explaining predictions for individual instances. The presented approach is general and can be used with all classification models that output probabilities. It is based on decomposition of a model's predictions on individual contributions of each attribute. Our method works for so called black box models such as support vector machines, neural networks, and nearest neighbor algorithms as well as for ensemble methods, such as boosting and random forests. We demonstrate that the generated… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
2
1
1
1

Citation Types

0
124
0
2

Year Published

2009
2009
2024
2024

Publication Types

Select...
6
3

Relationship

0
9

Authors

Journals

citations
Cited by 222 publications
(126 citation statements)
references
References 23 publications
0
124
0
2
Order By: Relevance
“…Prior research has examined two different sorts of "explanation" procedures for understanding predictive models: global explanation and instance-level explanation (Craven and Shavlik 1996, Martens et al 2007, Robnik-Šikonja and Kononenko 2008,Štrumbelj et al 2009,Štrumbelj and Kononenko 2010, Baehrens et al 2010. Global explanations provide improved understanding of the complete model, and its performance over the entire space of possible instances.…”
Section: Explaining Documents' Classificationsmentioning
confidence: 99%
“…Prior research has examined two different sorts of "explanation" procedures for understanding predictive models: global explanation and instance-level explanation (Craven and Shavlik 1996, Martens et al 2007, Robnik-Šikonja and Kononenko 2008,Štrumbelj et al 2009,Štrumbelj and Kononenko 2010, Baehrens et al 2010. Global explanations provide improved understanding of the complete model, and its performance over the entire space of possible instances.…”
Section: Explaining Documents' Classificationsmentioning
confidence: 99%
“…We use two general explanation methods IME and EX-PLAIN (Robnik-Šikonja and Kononenko, 2008;Štrumbelj et al, 2009). These two methods explain model's predictions as contributions of individual attributes.…”
Section: Introduction To General Explanation Methodology With Examplesmentioning
confidence: 99%
“…Unfortunately, complex models are also difficult to interpret. This can be alleviated either by sacrificing some prediction perforUnauthenticated Download Date | 5/10/18 4:34 AM mance and selection of transparent model or by using an explanation method that improves the interpretability of complex models, like the general explanation methodology that can be applied to any classification or regression model (Robnik-Šikonja and Kononenko, 2008;Štrumbelj, Kononenko and Robnik-Šikonja, 2009). …”
Section: Related Workmentioning
confidence: 99%
“…The first two datasets, cross and chess, are taken from Robnik-Sikonja and Kononenko (2008) and contain exactly one relevant interaction each. The third dataset, cube, is introduced here for the first time and has several interactions influencing the class membership.…”
Section: Illustrating the Relevance Of Interactions For Classificationmentioning
confidence: 99%