Due to today’s advancement in technology and businesses, fraud detection has become a critical component of financial transactions. Considering vast amounts of data in large datasets, it becomes more difficult to detect fraud transactions manually. In this research, we propose a combined method using both data mining and statistical tasks, utilizing feature selection, resampling and cost-...

In this paper, we consider Bayesian reinforcement learning (BRL) where actions incur costs in addition to rewards, and thus exploration has to be constrained in terms of the expected total cost while learning to maximize the expected longterm total reward. In order to formalize cost-sensitive exploration, we use the constrained Markov decision process (CMDP) as the model of the environment, in ...

We study binary classification in the presence of class-conditional random noise, where the learner gets to see labels that are flipped independently with some probability, and where the flip probability depends on the class. Our goal is to devise learning algorithms that are efficient and statistically consistent with respect to commonly used utility measures. In particular, we look at a famil...

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...

In this paper, we propose a new and general preprocessor algorithm, called CSRoulette, which converts any cost-insensitive classification algorithms into cost-sensitive ones. CSRoulette is based on cost proportional roulette sampling technique (called CPRS in short). CSRoulette is closely related to Costing, another cost-sensitive meta-learning algorithm, which is based on rejection sampling. U...

One problem of data-driven answer extraction in open-domain factoid question answering is that the class distribution of labeled training data is fairly imbalanced. This imbalance has a deteriorating effect on the performance of resulting classifiers. In this paper, we propose a method to tackle class imbalance by applying some form of cost-sensitive learning which is preferable to sampling. We...

We design an active learning algorithm for cost-sensitive multiclass classification: problems where different errors have different costs. Our algorithm, COAL, makes predictions by regressing to each label’s cost and predicting the smallest. On a new example, it uses a set of regressors that perform well on past data to estimate possible costs for each label. It queries only the labels that cou...

A popular approach to cost-sensitive learning is to rescale the classes according to their misclassification costs. Although this approach is effective in dealing with binary-class problems, recent studies show that it is often not so helpful when being applied to multiclass problems directly. This paper analyzes that why the traditional rescaling approach is often helpless on multi-class probl...

In this paper, we propose a new method for learning to rank. ‘Ranking SVM’ is a method for performing the task. It formulizes the problem as that of binary classification on instance pairs and performs the classification by means of Support Vector Machines (SVM). In Ranking SVM, the losses for incorrect classifications of instance pairs between different rank pairs are defined as the same. We n...

In the usual setting of Machine Learning, classifiers are typically evaluated by estimating their error rate (or equivalently, the classification accuracy) on the test data. However, this makes sense only if all errors have equal (uniform) costs. When the costs of errors differ between each other, the classifiers should be evaluated by comparing the total costs of the errors. Classifiers are ty...