- author = "Andrew Lensen",
- title = "Mining Feature Relationships in Data",
- booktitle = "EuroGP 2021: Proceedings of the 24th European Conference on Genetic Programming",
- year = "2021",
- editor = "Ting Hu and Nuno Lourenco and Eric Medvet",
- series = "LNCS",
- volume = "12691",
- publisher = "Springer Verlag",
- address = "Virtual Event",
- pages = "247--262",
- month = "7-9 " # apr,
- organisation = "EvoStar, Species",
- keywords = "genetic algorithms, genetic programming, Association Rule Mining, Feature Relationships, Feature Construction, Feature Analysis, Unsupervised Learning: Poster",
- isbn13 = "978-3-030-72811-3",
-
URL = "
https://arxiv.org/abs/2102.01355",
-
DOI = "
doi:10.1007/978-3-030-72812-0_16",
- size = "16 pages",
- abstract = "When faced with a new dataset, most practitioners begin by performing exploratory data analysis to discover interesting patterns and characteristics within data. Techniques such as association rule mining are commonly applied to uncover relationships between features (attributes) of the data. However, association rules are primarily designed for use on binary or categorical data, due to their use of rule-based machine learning. A large proportion of real-world data is continuous in nature, and discretisation of such data leads to inaccurate and less informative association rules. In this paper, we propose an alternative approach called feature relationship mining (FRM), which uses a genetic programming approach to automatically discover symbolic relationships between continuous or categorical features in data. To the best of our knowledge, our proposed approach is the first such symbolic approach with the goal of explicitly discovering relationships between features. Empirical testing on a variety of real-world datasets shows the proposed method is able to find high-quality, simple feature relationships which can be easily interpreted and which provide clear and non-trivial insight into data.",
-
notes = "Crossover within limited number of species. Parsimony
pressure: tree size penalty. UCI wine dataset
Flavonoids v
Proanthocyanidins.
http://www.evostar.org/2021/eurogp/ Part of \cite{Hu:2021:GP} EuroGP'2021 held in conjunction with EvoCOP2021, EvoMusArt2021 and EvoApplications2021",
