A Distance-Based Approach for Action Recommendation

  • Ronan Trepos
  • Ansaf Salleb
  • Marie-Odile Cordier
  • Véronique Masson
  • Chantal Gascuel
Part of the Lecture Notes in Computer Science book series (LNCS, volume 3720)


Rule induction has attracted a great deal of attention in Machine Learning and Data Mining. However, generating rules is not an end in itself because their applicability is not so straightforward. Indeed, the user is often overwhelmed when faced with a large number of rules.

In this paper, we propose an approach to lighten this burden when the user wishes to exploit such rules to decide which actions to do given an unsatisfactory situation. The method consists in comparing a situation to a set of classification rules. This is achieved using a suitable distance thus allowing to suggest action recommendations with minimal changes to improve that situation. We propose the algorithm Dakar for learning action recommendations and we present an application to an environmental protection issue. Our experiment shows the usefulness of our contribution in decision-making but also raises concerns about the impact of the redundancy of a set of rules in learning action recommendations of quality.


Decision support actionability rule-based classifier generalized Minkowski metrics maximally discriminant descriptions 


  1. 1.
    Agrawal, R., Imielinski, T., Swami, A.N.: Mining association rules between sets of items in large databases. In: Buneman, P., Jajodia, S. (eds.) Proceedings of the 1993 ACM SIGMOD, pp. 207–216. ACM Press, New York (1993)CrossRefGoogle Scholar
  2. 2.
    Cordier, M.-O.: SACADEAU: A decision-aid system to improve stream-water quality. ERCIM News. Special issue on Environmental Modelling (61), 35–36 (2005)Google Scholar
  3. 3.
    Duval, B., Salleb, A., Vrain, C.: Méthodes et mesures d’intérêt pour l’extraction de règles d’exception. Revue des Nouvelles Technologies de l’Information - Mesures de Qualité pour la Fouille de Données RNTI-E-1, 119–140 (2004)Google Scholar
  4. 4.
    Elovici, Y., Braha, D.: A decision-theoretic approach to data mining. IEEE Transactions on Systems, Man, and Cybernetics, Part A 33(1), 42–51 (2003)CrossRefGoogle Scholar
  5. 5.
    He, Z., Xu, X., Deng, S.: Data Mining for Actionable Knowledge: A Survey. In: ArXiv Computer Science e-prints (January 2005)Google Scholar
  6. 6.
    Hutchinson, A.: Metrics on terms and clauses. In: van Someren, M., Widmer, G. (eds.) ECML 1997. LNCS, vol. 1224, pp. 138–145. Springer, Heidelberg (1997)Google Scholar
  7. 7.
    Ichino, M., Yaguchi, H.: Generalized minkowski metrics for mixed feature-type data analysis. IEEE Transactions on Systems, Man, and Cybernetics 24(4), 698–708 (1994)CrossRefMathSciNetGoogle Scholar
  8. 8.
    Lavrač, N., Cestnik, B., Gamberger, D., Flach, P.: Decision support through subgroup discovery: Three case studies and the lessons learned. Machine Learning 57(1-2), 115–143 (2004)zbMATHCrossRefGoogle Scholar
  9. 9.
    Ling, C.X., Chen, T., Yang, Q., Cheng, J.: Mining optimal actions for profitable CRM. In: ICDM, pp. 767–770 (2002)Google Scholar
  10. 10.
    Liu, B., Hsu, W., Ma, Y.: Identifying non-actionable association rules. In: KDD 2001: Proceedings of the seventh ACM SIGKDD international conference on Knowledge discovery and data mining, pp. 329–334. ACM Press, New York (2001)CrossRefGoogle Scholar
  11. 11.
    Malerba, D., Esposito, F., Gioviale, V., Tamma, V.: Comparing dissimilarity measures in symbolic data analysis. In: Joint Conferences on New Techniques and Technologies for Statistcs and Exchange of Technology and Know-how (ETK-NTTS 2001), pp. 473–481 (2001)Google Scholar
  12. 12.
    Mitchell, T.M.: Generalization as search. Artif. Intell. 18(2), 203–226 (1982)CrossRefGoogle Scholar
  13. 13.
    Piatetsky-Shapiro, G., Matheus, C.: The interestingness of deviations. In: AAAI Workshop on Knowledge Discovery in Databases, pp. 25–36. AAAI Press, Menlo Park (1994)Google Scholar
  14. 14.
    Quinlan, J.R.: C4.5: programs for machine learning. Morgan Kaufmann Publishers Inc., San Francisco (1993)Google Scholar
  15. 15.
    De Raedt, L., Van Laer, W.: Inductive constraint logic. In: ALT 1995: Proceedings of the 6th International Conference on Algorithmic Learning Theory, pp. 80–94. Springer, Heidelberg (1995)Google Scholar
  16. 16.
    Ramon, J., Bruynooghe, M., Van Laer, W.: Distance measures between atoms. In: CompulogNet Area Meeting on Computational Logic and Machine Learing, University of Manchester, UK, May 1998, pp. 35–41 (1998)Google Scholar
  17. 17.
    Ras, Z.W., Tsay, L.-S.: Discovering extended action-rules (system dear). In: IIS, pp. 293–300 (2003)Google Scholar
  18. 18.
    Ras, Z.W., Wieczorkowska, A.: Action-rules: How to increase profit of a company. In: Zighed, D.A., Komorowski, J., Żytkow, J.M. (eds.) PKDD 2000. LNCS (LNAI), vol. 1910, pp. 587–592. Springer, Heidelberg (2000)CrossRefGoogle Scholar
  19. 19.
    Sebag, M.: Delaying the choice of bias: A disjunctive version space approach. In: ICML, pp. 444–452 (1996)Google Scholar
  20. 20.
    Sebag, M.: Distance induction in first order logic. In: Džeroski, S., Lavrač, N. (eds.) ILP 1997. LNCS, vol. 1297, pp. 264–272. Springer, Heidelberg (1997)Google Scholar
  21. 21.
    Silberschatz, A., Tuzhilin, A.: What makes patterns interesting in knowledge discovery systems. IEEE Trans. on Knowledge And Data Engineering 8, 970–974 (1996)CrossRefGoogle Scholar
  22. 22.
    Torgo, L.: Controlled redundancy in incremental rule learning. In: Brazdil, P.B. (ed.) ECML 1993. LNCS, vol. 667, pp. 185–195. Springer, Heidelberg (1993)Google Scholar
  23. 23.
    Yang, Q., Yin, J., Ling, C.X., Chen, T.: Postprocessing decision trees to extract actionable knowledge. In: ICDM, pp. 685–688 (2003)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2005

Authors and Affiliations

  • Ronan Trepos
    • 1
    • 2
  • Ansaf Salleb
    • 1
  • Marie-Odile Cordier
    • 1
  • Véronique Masson
    • 1
  • Chantal Gascuel
    • 2
  1. 1.IRISA-INRIARennes CedexFrance
  2. 2.INRA UMR SASRennes CedexFrance

Personalised recommendations