LAC: Library for associative classification

Francisco Padillo, José María Luna, Sebastián Ventura

Abstract: The goal of this paper is to introduce LAC, a new Java Library for Associative Classification. LAC is the first tool that covers the full taxonomy of this classification paradigm through 10 well-known proposals in the field. Furthermore, it includes several measures to quantify the quality of the solutions as well as different input/output data formats. Last but not least, the library also provides a framework to automate experimental studies, supporting both sequential and parallel executions. Thanks to the GPLv3 license, LAC is totally free, open-source and publicly available.