Binary classification

binary classifierbinarybinary categorizationbinary classifiersbinary outputbinary testclassificationsclassifyingconversion of continuous values into binary valuesconverted to a binary ones
Binary or binomial classification is the task of classifying the elements of a given set into two groups (predicting which group each one belongs to) on the basis of a classification rule.wikipedia
86 Related Articles

Qualitative property

qualitativequalitative dataqualitatively
This can be a categorical result or a binary classification (e.g., pass/fail, go/no go, conform/non-conform).

Classification rule

classifiersclassification testclassifier
A special kind of classification rule is binary classification, for problems in which there are only two classes.

Discretization

discretizeddiscretizingdichotomization
Binary classification is dichotomization applied to practical purposes, and in many practical binary classification problems, the two groups are not symmetric – rather than overall accuracy, the relative proportion of different types of errors is of interest.
Dichotomization is the special case of discretization in which the number of discrete classes is 2, which can approximate a continuous variable as a binary variable (creating a dichotomy for modeling purposes, as in binary classification).

Go/no go

go/no-goGO / NO-GOgo or no go
In general go/no go testing refers to a pass/fail test (or check) principle using two boundary conditions or a binary classification.

Support-vector machine

support vector machinesupport vector machinesSVM
Given a set of training examples, each marked as belonging to one or the other of two categories, an SVM training algorithm builds a model that assigns new examples to one category or the other, making it a non-probabilistic binary linear classifier (although methods such as Platt scaling exist to use SVM in a probabilistic classification setting).

Statistical classification

classificationclassifierclassifiers
Statistical classification is a problem studied in machine learning.
Classification can be thought of as two separate problems – binary classification and multiclass classification.

Probit model

probit regressionprobitBayesian probit regression
The purpose of the model is to estimate the probability that an observation with particular characteristics will fall into a specific one of the categories; moreover, classifying observations based on their predicted probabilities is a type of binary classification model.

Logistic regression

logit modellogisticlogistic model
The model itself simply models probability of output in terms of input, and does not perform statistical classification (it is not a classifier), though it can be used to make a classifier, for instance by choosing a cutoff value and classifying inputs with probability greater than the cutoff as one class, below the cutoff as the other; this is a common way to make a binary classifier.

Sensitivity and specificity

sensitivityspecificitysensitive
For example, in medicine sensitivity and specificity are often used, while in information retrieval precision and recall are preferred.

Machine learning

machine-learninglearningstatistical learning
Statistical classification is a problem studied in machine learning.
An SVM training algorithm is a non-probabilistic, binary, linear classifier, although methods such as Platt scaling exist to use SVM in a probabilistic classification setting.

False positives and false negatives

false positivefalse negativefalse positives
For example, in medical testing, a false positive (detecting a disease when it is not present) is considered differently from a false negative (not detecting a disease when it is present).
In medical testing, and more generally in binary classification, a false positive is an error in data reporting in which a test result improperly indicates presence of a condition, such as a disease (the result is positive), when in reality it is not present, while a false negative is an error in which a test result improperly indicates no presence of a condition (the result is negative), when in reality it is present.

Type I and type II errors

Type I errorfalse-positivefalse positive
Binary classification is dichotomization applied to practical purposes, and in many practical binary classification problems, the two groups are not symmetric – rather than overall accuracy, the relative proportion of different types of errors is of interest.

Diagnostic odds ratio

Taking the ratio of one of these groups of ratios yields a final ratio, the diagnostic odds ratio (DOR).
In medical testing with binary classification, the diagnostic odds ratio is a measure of the effectiveness of a diagnostic test.

F1 score

F-MeasureF-scoreF1
The F-score combines precision and recall into one number via a choice of weighing, most simply equal weighing, as the balanced F-score (F1 score).
In statistical analysis of binary classification, the F 1 score (also F-score or F-measure) is a measure of a test's accuracy.

Matthews correlation coefficient

Matthews Correlation
Some metrics come from regression coefficients: the markedness and the informedness, and their geometric mean, the Matthews correlation coefficient.
The Matthews correlation coefficient is used in machine learning as a measure of the quality of binary (two-class) classifications, introduced by biochemist Brian W. Matthews in 1975.

Accuracy and precision

accuracyprecisionaccurate
There are a number of other metrics, most simply the accuracy or Fraction Correct (FC), which measures the fraction of all instances that are correctly categorized; the complement is the Fraction Incorrect (FiC).
Accuracy is also used as a statistical measure of how well a binary classification test correctly identifies or excludes a condition.

Receiver operating characteristic

ROC curveAUCROC
A receiver operating characteristic curve, or ROC curve, is a graphical plot that illustrates the diagnostic ability of a binary classifier system as its discrimination threshold is varied.

Multiclass classification

multi-classmulti-class categorizationmulti-class classification
(Classifying instances into one of two classes is called binary classification.)

Predictive value of tests

predictive valuepredictive values
As a result, when converting a continuous value that is close to the cutoff to a binary one, the resultant positive or negative predictive value is generally higher than the predictive value given directly from the continuous value.
A conversion of continuous values into binary values can be performed, such as designating a pregnancy test as "positive" above a certain cutoff value, but this confers a loss of information and generally results in less accurate predictive values.

Medical test

diagnostic testdiagnostic testsdiagnostic testing
Tests whose results are of continuous values, such as most blood values, can artificially be made binary by defining a cutoff value, with test results being designated as positive or negative depending on whether the resultant value is higher or lower than the cutoff.
The classification of tests into either positive or negative gives a binary classification, with resultant ability to perform bayesian probability and performance metrics of tests, including calculations of sensitivity and specificity.

Kernel method

kernel trickkernel methodskernelized
For instance, a kernelized binary classifier typically computes a weighted sum of similarities

One-class classification

PU learningone-class classifiers
A similar problem is PU learning, in which a binary classifier is learned in a semi-supervised way from only positive and unlabeled sample points.

Positive and negative predictive values

positive predictive valuenegative predictive valuepositive
As a result, when converting a continuous value that is close to the cutoff to a binary one, the resultant positive or negative predictive value is generally higher than the predictive value given directly from the continuous value. The row ratios are Positive Predictive Value (PPV, aka precision) (TP/(TP+FP)), with complement the False Discovery Rate (FDR) (FP/(TP+FP)); and Negative Predictive Value (NPV) (TN/(TN+FN)), with complement the False Omission Rate (FOR) (FN/(TN+FN)).