Skip to main content
SpringerLink
Log in

Exceptional Model Mining

Supervised descriptive local pattern mining with complex target concepts

  • Published:
Data Mining and Knowledge Discovery Aims and scope Submit manuscript

Abstract

Finding subsets of a dataset that somehow deviate from the norm, i.e. where something interesting is going on, is a classical Data Mining task. In traditional local pattern mining methods, such deviations are measured in terms of a relatively high occurrence (frequent itemset mining), or an unusual distribution for one designated target attribute (common use of subgroup discovery). These, however, do not encompass all forms of “interesting”. To capture a more general notion of interestingness in subsets of a dataset, we develop Exceptional Model Mining (EMM). This is a supervised local pattern mining framework, where several target attributes are selected, and a model over these targets is chosen to be the target concept. Then, we strive to find subgroups: subsets of the dataset that can be described by a few conditions on single attributes. Such subgroups are deemed interesting when the model over the targets on the subgroup is substantially different from the model on the whole dataset. For instance, we can find subgroups where two target attributes have an unusual correlation, a classifier has a deviating predictive performance, or a Bayesian network fitted on several target attributes has an exceptional structure. We give an algorithmic solution for the EMM framework, and analyze its computational complexity. We also discuss some illustrative applications of EMM instances, including using the Bayesian network model to identify meteorological conditions under which food chains are displaced, and using a regression model to find the subset of households in the Chinese province of Hunan that do not follow the general economic law of demand.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Fig. 7
Fig. 8

Similar content being viewed by others

Notes

  1. We consider the exact search strategy to be a parameter of the algorithm.

  2. When the description language at hand is very expressive, and the dataset contains many numeric attributes, one can imagine that for every subset of the dataset at least one corresponding description exists.

  3. http://cran.r-project.org.

  4. Available from the Journal of Applied Econometrics Data Archive at http://econ.queensu.ca/jae/.

References

  • Agresti A (1990) Categorical data analysis. Wiley, New York

  • Aidt T, Tzannatos Z (2002) Unions and collective bargaining. The World Bank, Washington, DC

    Book  Google Scholar 

  • Anglin PM, Gençay R (1996) Semiparametric estimation of a hedonic price function. J Appl Econ 11(6):633–648

    Article  Google Scholar 

  • Atzmüller M, Lemmerich F (2009) Fast subgroup discovery for continuous target concepts. In: Proceedings of ISMIS, pp 35–44

  • Bay SD, Pazzani MJ (2001) Detecting group differences: mining contrast sets. Data Min Knowl Discov 5(3):213–246

    Article  MATH  Google Scholar 

  • Blockeel H, De Raedt L, Ramon J (1998) Top-down induction of clustering trees. In: Procedings of ICML, pp 55–63

  • Boley M, Grosskreutz H (2009) Non-redundant subgroup discovery using a closure system. In: Proceedings of ECML/PKDD, vol 1, pp 179–194

  • Breiman L, Friedman JH, Olshen RA, Stone CJ (1984) Classification and regression trees. Wadsworth & Brooks/Cole Advanced Books & Software, Monterey

    MATH  Google Scholar 

  • de Campos LM, Fernández-Luna JM, Huete JF (2004) Bayesian networks and information retrieval: an introduction to the special issue. Inf Process Manag 40(5):727–733

    Article  Google Scholar 

  • Carmona CJ, González P, del Jesus MJ, Herrera F (2010) NMEEF-SD: non-dominated multiobjective evolutionary algorithm for extracting fuzzy rules in subgroup discovery. IEEE Trans Fuzzy Syst 18(5):958–970

    Article  Google Scholar 

  • Chao C, Velicer C, Slezak JM, Jacobsen SJ (2009) Correlates for completion of 3-dose regimen of HPV vaccine in female members of a managed care organization. Mayo Clin Proc 84(10):864–870

    Article  Google Scholar 

  • Cook RD (1977) Detection of influential observation in linear regression. Technometrics 19(1):15–18

    MATH  MathSciNet  Google Scholar 

  • Cook RD, Weisberg S (1980) Characterizations of an empirical influence function for detecting influential cases in regression. Technometrics 22(4):495–508

    Article  MATH  MathSciNet  Google Scholar 

  • Cook RD, Weisberg S (1982) Residuals and influence in regression. Chapman & Hall, London

    MATH  Google Scholar 

  • Costanigro M, Mittelhammer RC, McCluskey JJ (2009) Estimating class-specific parametric models under class uncertainty: local polynomial regression clustering in an hedonic analysis of wine markets. J Appl Econ 24:1117–1135

    Article  MathSciNet  Google Scholar 

  • Davis GA (2003) Bayesian reconstruction of traffic accidents. Law Probab Risk 2:69–89

    Article  Google Scholar 

  • Díez FJ, Mira J, Iturralde E, Zubillaga S (1997) DIAVAL, a Bayesian expert system for echocardiography. Artif Intell Med 10:59–73

    Article  Google Scholar 

  • Dong G, Li J (1999) Efficient mining of emerging patterns: discovering trends and differences. In: Proceedings of KDD, pp 43–52

  • Dougherty C (2011) Introduction to econometrics, 4th edn. Oxford University Press, Oxford

    Google Scholar 

  • Duivesteijn W, Feelders A, Knobbe AJ (2012) Different slopes for different folks—mining for exceptional regression models with Cook’s distance. In: Proceedings of KDD, pp 868–876

  • Duivesteijn W, Knobbe AJ, Feelders A, van Leeuwen M (2010) Subgroup discovery meets Bayesian networks—an exceptional model mining approach. In: Proceedings of ICDM, pp 158–167

  • Duivesteijn W, Loza Mencía E, Fürnkranz J, Knobbe AJ (2012) Multi-label LeGo—enhancing multi-label classifiers with local patterns. In: Proceedings of IDA, pp 114–125

  • Friedman J, Fisher N (1999) Bump-hunting in high-dimensional data. Stat Comput 9(2):123–143

    Article  Google Scholar 

  • Friedman N, Linial M, Nachman I, Pe’er D (2000) Using Bayesian networks to analyze expression data. J Comput Biol 7(3/4):601–620

    Article  Google Scholar 

  • Galbrun E, Miettinen P (2012) From black and white to full color: extending redescription mining outside the Boolean world. Stat Anal Data Min 5(4):284–303

    Article  MathSciNet  Google Scholar 

  • Garriga GC, Heikinheimo H, Seppänen JK (2007) Cross-mining binary and numerical attributes. In: Proceedings of ICDM, pp 481–486

  • Gallo A, Miettinen P, Mannila H (2008) Finding subgroups having several descriptions: algorithms for redescription mining. In: Proceedings of SDM, pp 334–345

  • Gentleman JF, Wilk MB (1975) Detecting outliers II: supplementing the direct analysis of residuals. Biometrics 31:387–410

    Article  MATH  Google Scholar 

  • Goodman LA (1970) The multivariate analysis of qualitative data: interaction among multiple classifications. J Am Stat Assoc 65:226–256

    Article  Google Scholar 

  • Grosskreutz H, Rüping S (2009) On subgroup discovery in numerical domains. Data Min Knowl Discov 19(2):210–226

    Article  MathSciNet  Google Scholar 

  • Hand DJ, Adams NM, Bolton RJ (2002) Pattern detection and discovery, vol 2447. Lecture notes in computer science, Springer, Berlin

    MATH  Google Scholar 

  • Heckerman D, Geiger D, Chickering DM (1995) Learning Bayesian networks: the combination of knowledge and statistical data. Mach Learn 20:197–243

    MATH  Google Scholar 

  • Heikinheimo H, Fortelius M, Eronen J, Mannila H (2007) Biogeography of European land mammals shows environmentally distinct and spatially coherent clusters. J Biogeogr 34(6):1053–1064

    Article  Google Scholar 

  • Herrera F, Carmona CJ, González P, del Jesus MJ (2011) An overview on subgroup discovery: foundations and applications. Knowl Inf Syst 29(3):495–525

    Article  Google Scholar 

  • Hochberg Y, Tamhane A (1987) Multiple comparison procedures. Wiley, New York

    Book  MATH  Google Scholar 

  • Jensen RT, Miller NH (2008) Giffen behavior and subsistence consumption. Am Econ Rev 98(4):1553–1577

    Article  Google Scholar 

  • del Jesús MJ, González P, Herrera F, Mesonero M (2007) Evolutionary fuzzy rule induction process for subgroup discovery: a case study in marketing. IEEE Trans Fuzzy Syst 15(4):578–592

    Article  Google Scholar 

  • Jorge AM, Azevedo PJ, Pereira F (2006) Distribution rules with numeric attributes of interest. In: Proceedings of PKDD, pp 247–258

  • Klösgen W (1996) Explora: a multipattern and multistrategy discovery assistant. In: Advances in knowledge discovery and data mining. pp 249–271

  • Klösgen W (1998) Deviation and association patterns for subgroup mining in temporal, spatial, and textual data bases. In: Rough sets and current trends in computing. Springer, pp 1–18

  • Klösgen W (1999) Applications and research problems of subgroup mining. In: Proceedings of ISMIS, pp 1–15

  • Klösgen W (2002) Subgroup discovery. In: Handbook of data mining and knowledge discovery, chap. 16.3. Oxford University Press, New York

  • Knobbe AJ, Feelders A, Leman D (2012) Exceptional model mining. In: Data mining: foundations and intelligent paradigms, intelligent systems reference library, vol 24, pp 183–198

  • Knuth DE (1998) The art of computer programming, vol. 3: sorting and searching, 2nd edn. Addison-Wesley, Reading

    Google Scholar 

  • Kocev D, Vens C, Struyf J, Džeroski S (2013) Tree ensembles for predicting structured outputs. Pattern Recogn 46(3):817–833

    Article  Google Scholar 

  • Kohavi R (1995) The power of decision tables. In: Proceedings of ECML, pp 174–189

  • van de Koppel E, Slavkov I, Astrahantseff K, Schramm A, Schulte J, Vandesompele J, de Jong E, Dzeroski S, Knobbe AJ (2007) Knowledge discovery in neuroblastoma-related biological data. In: Data mining in functional genomics and proteomics workshop at PKDD 2007, Warsaw, Poland, pp 45–56

  • Kralj Novak P, Lavrač N, Webb GI (2009) Supervised descriptive rule discovery: a unifying survey of contrast set, emerging pattern and subgroup mining. J Mach Learn Res 10:377–403

    MATH  Google Scholar 

  • Kriegel H-P, Kröger P, Schubert E, Zimek A (2012) Outlier detection in arbitrarily oriented subspaces. In: Proceedings of ICDM, pp 379–388

  • Lavrač N, Flach P, Zupan B (1999) Rule evaluation measures: a unifying view. In: Proceedings of the ninth international workshop on inductive logic programming. Lecture notes in artificial intelligence, vol 1634, pp 174–185

  • Lavrač N, Kavšek B, Flach PA, Todorovski L (2004) Subgroup discovery with CN2-SD. J Mach Learn Res 5:153–188

    Google Scholar 

  • van Leeuwen M (2010) Maximal exceptions with minimal descriptions. Data Min Knowl Discov 21(2):259–276

    Article  MathSciNet  Google Scholar 

  • van Leeuwen M, Knobbe AJ (2011) Non-redundant subgroup discovery in large and complex data. In: Proceedings of ECML/PKDD, vol 3, pp 459–474

  • van Leeuwen M, Knobbe AJ (2012) Diverse subgroup set discovery. Data Min Knowl Discov 25(2):208–242

    Article  MathSciNet  Google Scholar 

  • Leman D, Feelders A, Knobbe AJ (2008) Exceptional model mining. In: Proceedings of ECML/PKDD, vol 2, pp 1–16

  • Lemmerich F, Becker M, Atzmüller M (2012) Generic pattern trees for exhaustive exceptional model mining. In: Proceedings of ECML/PKDD, vol 2, pp 277–292

  • Mampaey M, Nijssen S, Feelders A, Knobbe AJ (2012) Efficient algorithms for finding richer subgroup descriptions in numeric and nominal data. In: Proceedings of ICDM, pp 499–508

  • Marshall A (1895) Principles of economics. MacMillan and co, New York

    Google Scholar 

  • Meeng M, Knobbe AJ (2011) Flexible enrichment with Cortana—Software Demo. In: Proceedings of Benelearn, pp 117–119

  • Mitchell-Jones T et al (1999) The atlas of European mammals. Poyser natural history. Poyser, London

    Google Scholar 

  • Moore D, McCabe G (1993) Introduction to the practice of statistics. WH Freeman and Company, New York

    Google Scholar 

  • Morik K, Boulicaut JF, Siebes A (2005) Local pattern detection. Lecture notes in computer science, vol 3539, Springer, Heidelberg

  • Neil M, Fenton N, Tailor M (2005) Using Bayesian networks to model expected and unexpected operational losses. Risk Anal 25(4):963–972

    Article  Google Scholar 

  • Neter J, Kutner M, Nachtsheim CJ, Wasserman W (1966) Applied linear statistical models. WCB McGraw-Hill, Boston

    Google Scholar 

  • Paine RT (1966) Food web complexity and species diversity. Am Nat 100(910):65–75

    Article  Google Scholar 

  • Ramakrishnan N, Kumar D, Mishra B, Potts M, Helm RF (1995) Turning CARTwheels: an alternating algorithm for mining redescriptions. In: Proceedings of KDD, pp 837–844

  • Rezende L (2008) Econometrics of auctions by least squares. J Appl Econ 23:925–948

    Article  MathSciNet  Google Scholar 

  • Scholz M (2005) Knowledge-based sampling for subgroup discovery. In: Morik K, Boulicaut JF, Siebes A (eds) Local pattern detection. Lecture notes in computer science, vol 3539, Springer, Heidelberg, pp 171–189

  • Schubert E, Wolfe J, Tarnopolsky A (2004) Spectral centroid and timbre in complex, multiple instrumental textures. In: Proceedings of 8th international conference on music perception & cognition, pp 654–657

  • Siebes A (1995) Data surveying: foundations of an inductive query language. In: Proceedings of KDD, pp 269–274

  • Stengos T, Zacharias E (2006) Intertemporal pricing and price discrimination: a semiparametric hedonic analysis of the personal computer market. J Appl Econ 21:371–386

    Article  MathSciNet  Google Scholar 

  • Trohidis K, Tsoumakas G, Kalliris G, Vlahavas IP (2008) Multi-label classification of music into emotions. In: Proceedings of 9th international conference on music information retrieval, pp 325–330

  • Umek L, Zupan B (2011) Subgroup discovery in data sets with multi-dimensional responses. Intell Data Anal 15(4):533–549

    Google Scholar 

  • Verma T, Pearl J (1990) Equivalence and synthesis of causal models. In: Proceedings of UAI, pp 255–270

  • Whittaker J (1990) Graphical models in applied multivariate statistics. Wiley, New York

    MATH  Google Scholar 

  • Wrobel S (1997) An algorithm for multi-relational discovery of subgroups. In: Proceedings of PKDD, pp 78–87

  • Yang G, Le Cam L (2000) Asymptotics in statistics: some basic concepts. Springer, Berlin

  • Zhang B (2003) Regression clustering. In: Proceedings of ICDM, pp 451–458

  • Zimmermann A, De Raedt L (2009) Cluster-grouping: from subgroup discovery to clustering. Mach Learn 77(1):125–159

    Article  Google Scholar 

Download references

Acknowledgments

This research is supported in part by the Deutsche Forschungsgemeinschaft (DFG) within the Collaborative Research Center SFB 876 “Providing Information by Resource-Constrained Analysis”, project C1, and in part by the Netherlands Organisation for Scientific Research (NWO) under project number 612.065.822 (Exceptional Model Mining).

Author information

Authors and Affiliations

  1. Fakultät für Informatik, LS VIII, Technische Universität Dortmund, Dortmund, Germany

    Wouter Duivesteijn

  2. ICS, Utrecht University, Utrecht, the Netherlands

    Ad J. Feelders

  3. LIACS, Leiden University, Leiden, the Netherlands

    Arno Knobbe

Authors
  1. Wouter Duivesteijn
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Ad J. Feelders
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Arno Knobbe
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Wouter Duivesteijn.

Additional information

Responsible editor: M.J. Zaki.

This paper extends the previously published papers (Leman et al. 2008; Duivesteijn et al. 2010, 2012a).

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Duivesteijn, W., Feelders, A.J. & Knobbe, A. Exceptional Model Mining. Data Min Knowl Disc 30, 47–98 (2016). https://doi.org/10.1007/s10618-015-0403-4

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s10618-015-0403-4

Keywords

Mathematics Subject Classification

Search

Navigation