A logistic regression method for cost sensetive active learning

Direct marketing involves offering a product or service to a carefully selected group of customers, the ones expected to render the most profits. Active learning is a data mining policy which actively selects unlabeled instances for labeling. In this research our goal is to construct a model that minimizes the net acquisition cost of selection of instances for labeling and at the same time maximizes the net profit gained from approaching selected customers. We present a new framework which combines a cost-sensitive active learning algorithm with a logistic regression classifier. We evaluated the framework on two benchmark datasets. The results appear encouraging.