Data Science Day @ Columbia University

We present QuantMiner, a Data Mining tool for mining Quantitative Association Rules that is taking into consideration numerical attributes in the mining process without a binning/discretization a priori of the data. It exploits a recent and innovative research in using genetic algorithms for mining quantitative rules published in IJCAI 2007.   The system is based on a genetic algorithm that dynamically discovers “good” intervals in association rules by optimizing both the support and the confidence of the rules. The experiments on real and artificial databases have shown the usefulness of QuantMiner as an interactive, exploratory data-mining tool.    The software was published in the Journal of Machine Learning Research open source software.  http://jmlr.org/papers/v14/salleb-aouissi13a.html