Explaining Classifications For Individual Instances

Robnik–Šikonja, Marko; Kononenko, Igor

doi:10.1109/tkde.2007.190734

Cited by 222 publications

(126 citation statements)

References 23 publications

Supporting

Mentioning

124

Contrasting

Unclassified

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%

Explaining Data-Driven Document Classifications

Martens

Provost

2014

MISQ

241

188

View full text Add to dashboard Cite

Many document classification applications require human understanding of the reasons for data-driven classification decisions: by managers, client-facing employees, and the technical team. Predictive models treat documents as data to be classified, and document data are characterized by very high dimensionality, often with tens of thousands to millions of variables (words). Unfortunately, due to the high dimensionality, understanding the decisions made by document classifiers is very difficult. This paper begins by extending the most relevant prior theoretical model of explanations for intelligent systems to account for some missing elements.The main theoretical contribution of the work is the definition of a new sort of explanation as a minimal set of words (terms, more generally), such that removing all words within this set from the document changes the predicted class from the class of interest. We present an algorithm to find such explanations, as well as a framework to assess such an algorithm's performance. We demonstrate the value of the new approach with a case study from a real-world document classification task: classifying web pages as containing objectionable content, with the goal of allowing advertisers to choose not to have their ads appear there. A second empirical demonstration on news-story topic classification uses the 20 Newsgroups benchmark dataset. The results show the explanations to be concise and document-specific, and to be capable of providing better understanding of the exact reasons for the classification decisions, of the workings of the classification models, and of the business application itself. We also illustrate how explaining documents' classifications can help to improve data quality and model performance.

show abstract

Section: Explaining Documents' Classificationsmentioning

confidence: 99%

Explaining Data-Driven Document Classifications

Martens

Provost

2014

MISQ

241

188

View full text Add to dashboard Cite

show abstract

“…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%

Organizational Learning Supported by Machine Learning Models Coupled with General Explanation Methods: A Case of B2B Sales Forecasting

Bohanec¹,

Robnik–Šikonja

Borštnar

2017

Organizacija

View full text Add to dashboard Cite

Background and Purpose:The process of business to business (B2B) sales forecasting is a complex decision-making process. There are many approaches to support this process, but mainly it is still based on the subjective judgment of a decision-maker. The problem of B2B sales forecasting can be modeled as a classification problem. However, top performing machine learning (ML) models are black boxes and do not support transparent reasoning. The purpose of this research is to develop an organizational model using ML model coupled with general explanation methods. The goal is to support the decision-maker in the process of B2B sales forecasting. Design/Methodology/Approach: Participatory approach of action design research was used to promote acceptance of the model among users. ML model was built following CRISP-DM methodology and utilizes R software environment. Results: ML model was developed in several design cycles involving users. It was evaluated in the company for several months. Results suggest that based on the explanations of the ML model predictions the users' forecasts improved. Furthermore, when the users embrace the proposed ML model and its explanations, they change their initial beliefs, make more accurate B2B sales predictions and detect other features of the process, not included in the ML model. Conclusions:The proposed model promotes understanding, foster debate and validation of existing beliefs, and thus contributes to single and double-loop learning. Active participation of the users in the process of development, validation, and implementation has shown to be beneficial in creating trust and promotes acceptance in practice.

show abstract

“…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%

Detecting relevant variables and interactions in supervised classification

Carrizosa

Martín-Barragán

Morales

2011

European Journal of Operational Research

View full text Add to dashboard Cite

The widely used Support Vector Machine (SVM) method has shown to yield good results in Supervised Classification problems. When the interpretability is an important issue, then classification methods such as Classification Trees (CART) might be more attractive, since they are designed to detect the important predictor variables and, for each predictor variable, the critical values which are most relevant for classification. However, when interactions between variables strongly affect the class membership, CART may yield misleading information. Extending previous work of the authors, in this paper an SVM-based method is introduced. The numerical experiments reported show that our method is competitive against SVM and CART in terms of misclassification rates, and, at the same time, is able to detect critical values and variables interactions which are relevant for classification.

show abstract

Explaining Classifications For Individual Instances

Cited by 222 publications

References 23 publications

Explaining Data-Driven Document Classifications

Explaining Data-Driven Document Classifications

Organizational Learning Supported by Machine Learning Models Coupled with General Explanation Methods: A Case of B2B Sales Forecasting

Detecting relevant variables and interactions in supervised classification

Contact Info

Product

Resources

About