Prescriptive Analytics on Systems with Large Event Streams

Abstract

Business processes demand quick decisions to achieve constant adaptation to changes in search of improving performance and taking advantage of opportunities. One possibility is to solve the process computationally. This requires producing analytics that transform data into knowledge for decision-making. There are several types of analytics, this work introduce a line of research focused on prescriptive analytics, as the more advanced level, capable of calculating actions to be executed at the moment (operational decisions) or in the future (tactical decisions for short and medium term, strategic decisions for long term) to achieve a desired goal. The calculation of actions involves the process of business events flow as datastreams, the application of Soft Computing and Computational Intelligence techniques and algorithms and, derived from the need for low response times, the use of High Performance Computing.