TTO_Grant Catalogue Grant Catalogue | Page 33

Profit-Driven Data Analytics: New Algorithms and Business Applications ABSTRACT The rapid growth in data capture and computational power has led to an increasing focus on data-driven research. So far, most of the research is focused on explanatory modeling, while predictive modeling has been less investigated. It is exactly this gap that will be addressed in this project by taking a profit-driven approach. a. Definition of a generic framework for profit-based classification performance measurement b. In-depth analysis of the dependencies between the parameters in the profit-based framework c. Developing statistical and heuristic based classification algorithms using the defined profit evaluation metrics Industrial Engineering In this project, we will undertake the following three main research objectives (RO): Doç. Dr. Ekrem Duman DEPARTMENT Industrial Engineering CONTACT [email protected] FUNDING SCHEME TÜBİTAK 2539 - FWO START DATE 10/1/13 DURATION 24 months OZU BUDGET 199,420.00 TL 2013 National Grants In the literature, numerous metrics have been proposed for measuring and comparing the performances of alternative classifiers. However, these performance measures are typically based on a statistical criterion without explicitly taking the costs and benefits into account. Hence, these often used performance metrics are not aligned with profit maximization, the main goal in a business context. 33