Classification is a data mining technique which is utilized to predict the future by using available data and aims to discover hidden relationships between variables and classes. Since the cost component is crucial in most real life classification problems and most traditional classification methods work for the purpose of correct classification, developing cost-sensitive classifiers which mini...

This article addresses the question of how to deal with text categorization when the set of documents to be classified belong to different languages. The figures we provide demonstrate that cross-lingual classification where a classifier is trained using one language and tested against another is possible and feasible provided we translate a small number of words: the most relevant terms for cl...

Learning from data streams has been an important open research problem in the era of big data analytics. This paper investigates supervised machine learning techniques for mining data streams with application to online anomaly detection. Unlike conventional machine learning tasks, machine learning from data streams for online anomaly detection has several challenges: (i) data arriving sequentia...

i,y with features x and label y. The computation of this sensitivity value is governed by the actual online update where we compute the derivative of the change in the prediction as a function of the importance weight w for a hypothetical example with cost 0 or cost 1 and the same features. This is possible for essentially all online update rules on importance weighted examples and it correspon...

The rows represent the actual patient status, and the columns represent the diagnosis made by the doctor. For instance, on any correct diagnosis, the society pays no (additional) cost. However, if an H1N1-infected patient is predicted as coldinfected or healthy, the whole society may suffer from a huge amount of cost. On the other hand, if a cold-infected patient is predicted as healthy, the so...

We study the problem of learning classifiers with a fairness constraint, with three main contributions towards the goal of quantifying the problem’s inherent tradeoffs. First, we relate two existing fairness measures to cost-sensitive risks. Second, we show that for cost-sensitive classification and fairness measures, the optimal classifier is an instance-dependent thresholding of the class-pro...

In time series classification, two antagonist notions are at stake. On the one hand, in most cases, the sooner the time series is classified, the more rewarding. On the other hand, an early classification is more likely to be erroneous. Most of the early classification methods have been designed to take a decision as soon as su cient level of reliability is reached. However, in many application...

In test cost-sensitive decision systems, it is difficulty for us to find an optimal attribute set and construct a quality classifier with limited cost. The minimal test cost-sensitive attribute reduction is proposed to address the former problem. However, it is inevitable to remove some good even better attributes in the minimal test cost-sensitive attribute reduction. As a result, the classifi...

We present a theoretical analysis of F -measures for binary, multiclass and multilabel classification. These performance measures are non-linear, but in many scenarios they are pseudo-linear functions of the per-class false negative/false positive rate. Based on this observation, we present a general reduction of F measure maximization to cost-sensitive classification with unknown costs. We the...

A commonly used approach to multiclass classification is to replace the 0− 1 loss with a convex surrogate so as to make empirical risk minimization computationally tractable. Previous work has uncovered sufficient and necessary conditions for the consistency of the resulting procedures. In this paper, we strengthen these results by showing how the 0− 1 excess loss of a predictor can be upper bo...