Comparing apples and oranges: measuring differences between exploratory data mining results

DOI10.1007/s10618-012-0275-9zbMath1260.68347arXiv1902.07165MaRDI QIDQ1944984

Nikolaj Tatti, Jilles Vreeken

Publication date: 28 March 2013

Published in: Data Mining and Knowledge Discovery (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/1902.07165

zbMATH Keywords

distance; tiling; binary data; maximum entropy model; exploratory data mining; iterative data mining

Mathematics Subject Classification ID

68T05: Learning and adaptive systems in artificial intelligence

94A17: Measures of information, entropy

Related Items

Summarizing and understanding large graphs, Handling noise in Boolean matrix factorization, The PRIMPING routine -- tiling through proximal alternating linearized minimization, Comparing apples and oranges: measuring differences between exploratory data mining results, Factorizing Boolean matrices using formal concepts and iterative usage of essential entries, Enriched spatial comparison of clusterings through discovery of deviating subspaces

Uses Software

• Krimp

Cites Work

• Unnamed Item
• Mixed-membership naive Bayes models
• Krimp: mining itemsets that compress
• Summarizing transactional databases with overlapped hyperrectangles
• Computational complexity of queries based on itemsets
• An approximation ratio for biclustering
• On the positive-negative partial set cover problem
• I-divergence geometry of probability distributions and minimization problems
• Measures of diversity in classifier ensembles and their relationship with the ensemble accuracy
• Summarizing categorical data by clustering attributes
• Comparing apples and oranges: measuring differences between exploratory data mining results
• Discovery Science
• Generalized Iterative Scaling for Log-Linear Models