Results 1  10
of
123
An Empirical Comparison of Voting Classification Algorithms: Bagging, Boosting, and Variants
 MACHINE LEARNING
, 1999
"... Methods for voting classification algorithms, such as Bagging and AdaBoost, have been shown to be very successful in improving the accuracy of certain classifiers for artificial and realworld datasets. We review these algorithms and describe a large empirical study comparing several variants in co ..."
Abstract

Cited by 582 (2 self)
 Add to MetaCart
Methods for voting classification algorithms, such as Bagging and AdaBoost, have been shown to be very successful in improving the accuracy of certain classifiers for artificial and realworld datasets. We review these algorithms and describe a large empirical study comparing several variants in conjunction with a decision tree inducer (three variants) and a NaiveBayes inducer.
The purpose of the study is to improve our understanding of why and
when these algorithms, which use perturbation, reweighting, and
combination techniques, affect classification error. We provide a
bias and variance decomposition of the error to show how different
methods and variants influence these two terms. This allowed us to
determine that Bagging reduced variance of unstable methods, while
boosting methods (AdaBoost and Arcx4) reduced both the bias and
variance of unstable methods but increased the variance for NaiveBayes,
which was very stable. We observed that Arcx4 behaves differently
than AdaBoost if reweighting is used instead of resampling,
indicating a fundamental difference. Voting variants, some of which
are introduced in this paper, include: pruning versus no pruning,
use of probabilistic estimates, weight perturbations (Wagging), and
backfitting of data. We found that Bagging improves when
probabilistic estimates in conjunction with nopruning are used, as
well as when the data was backfit. We measure tree sizes and show
an interesting positive correlation between the increase in the
average tree size in AdaBoost trials and its success in reducing the
error. We compare the meansquared error of voting methods to
nonvoting methods and show that the voting methods lead to large
and significant reductions in the meansquared errors. Practical
problems that arise in implementing boosting algorithms are
explored, including numerical instabilities and underflows. We use
scatterplots that graphically show how AdaBoost reweights instances,
emphasizing not only "hard" areas but also outliers and noise.
SMOTE: Synthetic Minority Oversampling Technique
 Journal of Artificial Intelligence Research
, 2002
"... An approach to the construction of classifiers from imbalanced datasets is described. A dataset is imbalanced if the classification categories are not approximately equally represented. Often realworld data sets are predominately composed of ``normal'' examples with only a small percentag ..."
Abstract

Cited by 354 (22 self)
 Add to MetaCart
An approach to the construction of classifiers from imbalanced datasets is described. A dataset is imbalanced if the classification categories are not approximately equally represented. Often realworld data sets are predominately composed of ``normal'' examples with only a small percentage of ``abnormal'' or ``interesting'' examples. It is also the case that the cost of misclassifying an abnormal (interesting) example as a normal example is often much higher than the cost of the reverse error. Undersampling of the majority (normal) class has been proposed as a good means of increasing the sensitivity of a classifier to the minority class. This paper shows that a combination of our method of oversampling the minority (abnormal) class and undersampling the majority (normal) class can achieve better classifier performance (in ROC space) than only undersampling the majority class. This paper also shows that a combination of our method of oversampling the minority class and undersampling the majority class can achieve better classifier performance (in ROC space) than varying the loss ratios in Ripper or class priors in Naive Bayes. Our method of oversampling the minority class involves creating synthetic minority class examples. Experiments are performed using C4.5, Ripper and a Naive Bayes classifier. The method is evaluated using the area under the Receiver Operating Characteristic curve (AUC) and the ROC convex hull strategy.
Analysis and Visualization of Classifier Performance: Comparison under Imprecise Class and Cost Distributions
 In Proceedings of the Third International Conference on Knowledge Discovery and Data Mining
, 1997
"... Applications of inductive learning algorithms to realworld data mining problems have shown repeatedly that using accuracy to compare classifiers is not adequate because the underlying assumptions rarely hold. We present a method for the comparison of classifier performance that is robust to imprecis ..."
Abstract

Cited by 281 (14 self)
 Add to MetaCart
(Show Context)
Applications of inductive learning algorithms to realworld data mining problems have shown repeatedly that using accuracy to compare classifiers is not adequate because the underlying assumptions rarely hold. We present a method for the comparison of classifier performance that is robust to imprecise class distributions and misclassification costs. The ROC convex hull method combines techniques from ROC analysis, decision analysis and computational geometry, and adapts them to the particulars of analyzing learned classifiers. The method is efficient and incremental, minimizes the management of classifier performance data, and allows for clear visual comparisons and sensitivity analyses. Introduction When mining data with inductive methods, we often experiment with a wide variety of learning algorithms, using different algorithm parameters, varying output threshold values, and using different training regimens. Such experimentation yields a large number of classifiers to be evaluated a...
Robust Classification for Imprecise Environments
, 1989
"... In realworld environments it is usually difficult to specify target operating conditions precisely. This uncertainty makes building robust classification systems problematic. We present a method for the comparison of classifier performance that is robust to imprecise class distributions and misclas ..."
Abstract

Cited by 279 (14 self)
 Add to MetaCart
(Show Context)
In realworld environments it is usually difficult to specify target operating conditions precisely. This uncertainty makes building robust classification systems problematic. We present a method for the comparison of classifier performance that is robust to imprecise class distributions and misclassification costs. The ROC convex hull method combines techniques from ROC analysis, decision analysis and computational geometry, and adapts them to the particulars of analyzing learned classifiers. The method is efficient and incremental, minimizes the management of classifier performance data, and allows for clear visual comparisons and sensitivity analyses. We then show that it is possible to build a hybrid classifier that will perform at least as well as the best available classifier for any target conditions. This robust performance extends across a wide variety of comparison frameworks, including the optimization of metrics such as accuracy, expected cost, lift, precision, recall, and ...
Tree Induction for Probabilitybased Ranking
, 2002
"... Tree induction is one of the most effective and widely used methods for building classification models. However, many applications require cases to be ranked by the probability of class membership. Probability estimation trees (PETs) have the same attractive features as classification trees (e.g., c ..."
Abstract

Cited by 142 (4 self)
 Add to MetaCart
Tree induction is one of the most effective and widely used methods for building classification models. However, many applications require cases to be ranked by the probability of class membership. Probability estimation trees (PETs) have the same attractive features as classification trees (e.g., comprehensibility, accuracy and efficiency in high dimensions and on large data sets). Unfortunately, decision trees have been found to provide poor probability estimates. Several techniques have been proposed to build more accurate PETs, but, to our knowledge, there has not been a systematic experimental analysis of which techniques actually improve the probabilitybased rankings, and by how much. In this paper we first discuss why the decisiontree representation is not intrinsically inadequate for probability estimation. Inaccurate probabilities are partially the result of decisiontree induction algorithms that focus on maximizing classification accuracy and minimizing tree size (for example via reducederror pruning). Larger trees can be better for probability estimation, even if the extra size is superfluous for accuracy maximization. We then present the results of a comprehensive set of experiments, testing some straghtforward methods for improving probabilitybased rankings. We show that using a simple, common smoothing methodthe Laplace correctionuniformly improves probabilitybased rankings. In addition, bagging substantioJly improves the rankings, and is even more effective for this purpose than for improving accuracy. We conclude that PETs, with these simple modifications, should be considered when rankings based on classmembership probability are required.
Data Mining for Direct Marketing: Problems and Solutions
 Proceedings of
, 1998
"... Direct marketing is a process of identifying likely buyers of certain products and promoting the products accordingly. It is increasingly used by banks, insurance companies, and the retail industry. Data mining can provide an effective tool for direct marketing. During data mining, several specific ..."
Abstract

Cited by 133 (0 self)
 Add to MetaCart
Direct marketing is a process of identifying likely buyers of certain products and promoting the products accordingly. It is increasingly used by banks, insurance companies, and the retail industry. Data mining can provide an effective tool for direct marketing. During data mining, several specific problems arise. For example, the class distribution is extremely imbalanced (the response rate is about 1~), the predictive accuracy is no longer suitable for evaluating learning methods, and the number of examples can be too large. In this paper, we discuss methods of coping with these problems based on our experience on directmarketing projects using data mining. 1
Decision Tree Induction Based on Efficient Tree Restructuring
 Machine Learning
, 1996
"... . The ability to restructure a decision tree efficiently enables a variety of approaches to decision tree induction that would otherwise be prohibitively expensive. Two such approaches are described here, one being incremental tree induction (ITI), and the other being nonincremental tree induction ..."
Abstract

Cited by 127 (5 self)
 Add to MetaCart
. The ability to restructure a decision tree efficiently enables a variety of approaches to decision tree induction that would otherwise be prohibitively expensive. Two such approaches are described here, one being incremental tree induction (ITI), and the other being nonincremental tree induction using a measure of tree quality instead of test quality (DMTI). These approaches and several variants offer new computational and classifier characteristics that lend themselves to particular applications. Keywords: decision tree, incremental induction, direct metric, binary test, example incorporation, missing value, tree transposition, installed test, virtual pruning, update cost. 1. Introduction Decision tree induction offers a highly practical method for generalizing from examples whose class membership is known. The most common approach to inducing a decision tree is to partition the labelled examples recursively until a stopping criterion is met. The partition is defined by selectin...
C4.5, Class Imbalance, and Cost Sensitivity: Why Undersampling beats Oversampling
, 2003
"... This paper takes a new look at two sampling schemes commonly used to adapt machine learning algorithms to imbalanced classes and misclassification costs. It uses a performance analysis technique called cost curves to explore the interaction of over and undersampling with the decision tree learner C4 ..."
Abstract

Cited by 85 (3 self)
 Add to MetaCart
(Show Context)
This paper takes a new look at two sampling schemes commonly used to adapt machine learning algorithms to imbalanced classes and misclassification costs. It uses a performance analysis technique called cost curves to explore the interaction of over and undersampling with the decision tree learner C4.5. C4.5 was chosen as, when combined with one of the sampling schemes, it is quickly becoming the community standard when evaluating new cost sensitive learning algorithms. This paper shows that using C4.5 with undersampling establishes a reasonable standard for algorithmic comparison. But it is recommended that the cheapest class classifier be part of that standard as it can be better than undersampling for relatively modest costs. Oversampling, however, shows little sensitivity, there is often little difference in performance when misclassification costs are changed. 1.
Explicitly Representing Expected Cost: An Alternative to ROC Representation
 In Proceedings of the Sixth ACM SIGKDD International Conference on Knowledge Discovery and Data Mining
, 2000
"... This paper proposes an alternative to ROC representation, in which the expected cost of a classifier is represented explicitly. This expected cost representation maintains many of the advantages of ROC representation, but is easier to understand. It allows the experimenter to immediately see the ran ..."
Abstract

Cited by 83 (11 self)
 Add to MetaCart
(Show Context)
This paper proposes an alternative to ROC representation, in which the expected cost of a classifier is represented explicitly. This expected cost representation maintains many of the advantages of ROC representation, but is easier to understand. It allows the experimenter to immediately see the range of costs and class frequencies where a particular classifier is the best and quantitatively how much better it is than other classifiers. This paper demonstrates there is a point/line duality between the two representations. A point in ROC space representing a classifier becomes a line segment spanning the full range of costs and class frequencies. This duality produces equivalent operations in the two spaces, allowing most techniques used in ROC analysis to be readily reproduced in the cost space.
Searching for Dependencies in Bayesian Classifiers
, 1996
"... Naive Bayesian classifiers which make independence assumptions perform remarkably well on some data sets but poorly on others. We explore ways to improve the Bayesian classifier by searching for dependencies among attributes. We propose and evaluate two algorithms for detecting dependencies among at ..."
Abstract

Cited by 74 (5 self)
 Add to MetaCart
Naive Bayesian classifiers which make independence assumptions perform remarkably well on some data sets but poorly on others. We explore ways to improve the Bayesian classifier by searching for dependencies among attributes. We propose and evaluate two algorithms for detecting dependencies among attributes and show that the backward sequential elimination and joining algorithm provides the most improvement over the naive Bayesian classifier. The domains on which the most improvement occurs are those domains on which the naive Bayesian classifier is significantly less accurate than a decision tree learner. This suggests that the attributes used in some common databases are not independent conditioned on the class and that the violations of the independence assumption that affect the accuracy of the classifier can be detected from training data. 23.1 Introduction The Bayesian classifier (Duda