Granularity-driven sequential three-way decisions: A cost-sensitive approach to classification

Sequential three-way decision (S3WD) is a multi-stage decision-making progress that emulates human cognition. S3WD employs coarse-to-fine information granularity and uses various types of costs to determine thresholds to make appropriate decisions. To date, however, few existing models discuss the construction of granules or consider costs in the decision process. This paper describes efforts to develop a granularity-driven sequential three-way decision model to address these two issues, and handle dual-constraint satisfaction problems considering both decision process and decision result costs. A key feature of the model is the incorporation of information granularity into the decision-making process. The model also incorporates a cost structure that accounts for the costs of both the decision process and the decision result. Using this model, we design two algorithms to minimize the cost of the decision process or the cost of the decision result. Our experimental results validate the effectiveness of the algorithms and the viability of the new model. (C) 2019 Elsevier Inc. All rights reserved.