Reducción de tamaño en Modelos de Reglas de Asociación: Una revisión sistemática de la literatura

• Autores: Julio César Díaz Vera, Guillermo Manuel Negrín Ortiz, Carlos Molina Fernández , María- Amparo Vila Miranda
• Localización: Revista Cubana de Ciencias Informáticas, ISSN-e 2227-1899, Vol. 15, Nº. 3, 2021
• Idioma: español
• Títulos paralelos:
  • Size reduction in Association Rules Models: A systematic literature review
• Enlaces
  • Texto completo
• Resumen
  • español

    Las Reglas de Asociación constituyen una de las tareas de minería de datos más estudiadas y aplicadas quizás porque su representación hace que sean fácilmente aceptadas e interpretadas por agentes humanos. Su principal debilidad está asociada a la gran cantidad de reglas que son generadas para casos relativamente sencillos y que hacen imposible su análisis manual para determinar cuáles son las reglas relevantes. El objetivo de este trabajo es ejecutar una revisión sistemática de la literatura en el campo de la reducción del tamaño de los modelos de reglas de asociación con vistas a caracterizar y presentar el estado del arte de esta temática e identificar nuevas oportunidades de investigación. El análisis de los resultados muestra que la mayoría de los esfuerzos se enfocan hacia la eliminación de reglas redundantes pero este enfoque se está desplazando desde definiciones de redundancia asociadas a la estructura de las reglas hacia la inclusión del conocimiento de los usuarios dentro del proceso.

  • English

    Association Rules are one of the most studied and applied techniques in Data Mining. This is because they are easily accepted an interpreted by human agents. Association Rules main handicap is the great cardinality of models that even in simple datasets produce too many rules to be, manually, analyzed by experts in order to find those that are relevant ones. The objective of this paper is to carry out a systematic literature review in the field of size reduction in association rules models, to characterize and present the state of the art of this field. From the analysis of the results, it could be observed that most works focus on redundancy elimination but they are moving from redundancy definition associated to rule structure to redundancy definitions based on user knowledge and preference.

• Referencias bibliográficas
  • Taluja, S,Bhupal, J,Krishnan, S. (2020). A Survey Paper on DNA-Based Data Storage. Emerging Trends in Information Technology and Engineering:...
  • Tirnauca, C,Balcazar, J. L,Gomez-Perez, D. (2020). Closed-Set-Based Discovery of Representative Association Rules. International Journal of...
  • Keele, Staffs. (2007). Guidelines for performing systematic literature reviews in software engineering.. Technical report, Ver. 2.3 EBSE Technical...
  • Shaharanee, Izwan Nizal Mohd,Jamil. (2015). A framework for interestingness measures for association rules with discrete and continuous attributes...
  • Bastide, Yves. (2000). Mining minimal non-redundant association rules using frequent closed itemsets.. Springer, Berlin, Heidelberg.
  • Balcazar, Jose L. (2010). Redundancy, Deduction Schemes, and Minimum-Size Bases for Association Rules,. Logical Methods in Computer Science....
  • Sudarsanam, Nandan. (2020). Rate of change analysis for interestingness measures.. Knowledge and Information Systems. 62. 239
  • Djenouri, Youcef. (2018). Discovering strong meta association rules using bees swarm optimization.. En Pacific-Asia Conference on Knowledge...
  • Weidner, Daniel,Atzmueller, Martin,Dietmar, Seipel. (2019). Finding Maximal Non-redundant Association Rules in Tennis Data. Springer, Cham.
  • Boudane, Abdelhamid. (2017). Enumerating non-redundant association rules using satisfiability.. . Springer, Cham.
  • De Carvalho, Veronica Oliveira. (2017). Ranking Association Rules by Clustering Through Interestingness.. Springer, Cham.
  • Kryszkiewicz, Marzena. (2018). Representative Rule Templates for Association Rules Satisfying Multiple Canonical Evaluation Criteria.. Springer,...
  • Chen, Chun-Hao. (2019). Post-Analysis Framework for Mining Actionable Patterns Using Clustering and Genetic Algorithms. IEEE Access. 7. 108101
  • Dong, Xiangjun. (2020). An efficient method for pruning redundant negative and positive association rules. Neurocomputing. 393. 245
  • Chiclana, Francisco. (2018). Arm-Amo: an efficient association rule mining algorithm based on animal migration optimization.. Knowledge-Based...
  • Shukla, Shekhar,Mohanty, B. K,Kumar, Ashwani. (2017). A Multi Attribute Value Theory approach to rank association rules for leveraging better...
  • Ait-Mlouk, Addi,Agouti, Tarik,Gharnati, Fatima. (2017). Mining and prioritization of association rules for big data: multi-criteria decision...
  • Jin, Maozhu,Wang, Hua,Zhang, Qian. (2019). Association rules redundancy processing algorithm based on hypergraph in data mining. Cluster Computing....
  • Kryszkiewicz, Marzena. (2016). A lossless representation for association rules satisfying multiple evaluation criteria.. Springer, Berlin,...
  • Kryszkiewicz, Marzena. (2015). Dependence factor for association rules. Springer, Cham.
  • De Padua, Renan,Rezende, Solange Oliveira,De Carvalho, Veronica Oliveira. (2014). Post-processing association rules using networks and transductive...
  • De Padua, Renan,De Carvalho, Veronica Oliveira,REZENDE, Solange Oliveira. (2016). Post-processing Association Rules: A Network Based Label...
  • Cifarelli, Bruno Braga,Miani, Rafael Garcia Leonel. (2020). Weakly Supervised Learning Algorithm to Eliminate Irrelevant Association Rules...
  • Heraguemi,Kamel, Nadjet,DRIAS, Habiba. (2016). Multi-objective bat algorithm for mining interesting association rules.. Springer, Cham.
  • Gireesha, O,Obulesu, O. Tkar. (2017). Efficient Mining of Top-k Association Rules on Real-Life Datasets. En Proceedings of the 5th International...
  • (2020). CORE. Computing research & education.
  • (2019). JCR. SJR: Scientific Journal Rankings.