Explaining Classifications For Individual Instances
نویسندگان
چکیده
منابع مشابه
Explaining Naïve Bayes Classifications
Naïve Bayes classifiers, a popular tool for predicting the labels of query instances, are typically learned from a training set. However, since many training sets contain noisy data, a classifier user may be reluctant to blindly trust a predicted label. We present a novel graphical explanation facility for Naïve Bayes classifiers that serves three purposes. First, it transparently explains the ...
متن کاملExplaining Data-Driven Document Classifications
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 t...
متن کاملExplaining instance classifications with interactions of subsets of feature values
In this paper, we present a novel method for explaining the decisions of an arbitrary classifier, independent of the type of classifier. The method works at the instance level, decomposing the model’s prediction for an instance into the contributions of the attributes’ values. We use several artificial data sets and several different types of models to show that the generated explanations refle...
متن کاملExplaining Individual Differences in Spelling Ability
$ $ & This article considers the differences between good and poor spellers. The article is organized into four basic sections that consider the factors involved in learning to spell and the relationship between reading and spelling, spelling ability in good and poor readers, the good reader–poor speller paradox, and individual differences in good and poor spellers. The major conclusion reached...
متن کاملExplaining Individual Response using Aggregated Data
Empirical analysis of individual response behavior is sometimes limited due to the lack of explanatory variables at the individual level. In this paper we put forward a new approach to estimate the effects of covariates on individual response, where the covariates are unknown at the individual level but observed at some aggregated level. This situation may, for example, occur if the response va...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
ژورنال
عنوان ژورنال: IEEE Transactions on Knowledge and Data Engineering
سال: 2008
ISSN: 1041-4347
DOI: 10.1109/tkde.2007.190734