Using Fuzzy Logic for Product Matching

Conference paper
Part of the Advances in Intelligent Systems and Computing book series (AISC, volume 246)

Abstract

Product matching is a special type of entity matching, and it is used to identify similar products and merging products based on their attributes. Product attributes are not always crisp values and may take values from a fuzzy domain. The attributes with fuzzy data values are mapped to fuzzy sets by associating appropriate membership degree to the attribute values. The crisp data values are fuzzified to fuzzy sets based on the linguistic terms associated with the attribute domain. Recently, matching dependencies (MDs) are used to define matching rules for entity matching. In this study, MDs defined with fuzzy attributes are extracted from product offers and are used as matching rules. Matching rules can aid product matching techniques in identifying the key attributes for matching. The proposed solution is applied on a specific problem of product matching, and the results show that the matching rules improve matching accuracy.

Keywords

Product matching Data integration Fuzzy logic Matching dependency 

References

  1. 1.
    Christen, P. (2012), A Survey of Indexing Techniques for Scalable Record Linkage and Deduplication, IEEE Transactions on, Knowledge and Data Engineering, 24(9), 1537–1555.Google Scholar
  2. 2.
    Divesh S and Suresh V(2010), Information Theory for Data Management, Tutorial in Proceedings of the ACM SIGMOD Conference on Management of Data, 1255–1256.Google Scholar
  3. 3.
    Fan W, Geerts F, (2011) Foundations of Data Quality Management, Synthesis Lectures on Data Management, Morgan & Claypool Publishers.Google Scholar
  4. 4.
    Fan, W., Gao, H., Jia, X., Li, J, and Ma, S. (2011). Dynamic Constraints for Record Matching. The VLDB Journal, 20(4), 495–520.Google Scholar
  5. 5.
    Köpcke, H., and Rahm, E. (2010). Frameworks for Entity Matching: A Comparison. Data & Knowledge Engineering, 69(2),197-210.Google Scholar
  6. 6.
    Liu, J., Li, J., Liu, C., & Chen, Y. (2012). Discover Dependencies from Data-A Review. IEEE Transactions on Knowledge and Data Engineering, 24(2), 251–264.Google Scholar
  7. 7.
    Papadimitriou, P., P. Tsaparas, A. Fuxman and L. Getoor, (2013). TACI: Taxonomy Aware Catalog Integration, IEEE Transactions on Knowledge and Data Engineering, 25: 1643–1655.Google Scholar
  8. 8.
    Song, S. and L. Chen, (2009). Discovering Matching Dependencies, In Proceedings of the 18th ACM Conference on Information and Knowledge Management, pp: 1421–1424.Google Scholar
  9. 9.
    Song, S., L. Chen and J.X. Yu, (2010). Extending Matching Rules with Conditions, Proceedings of the 8th International Workshop on Quality in Databases, 13–17 September.Google Scholar
  10. 10.
    Wang, S. L., Shen, J. W., & Hong, T. P. (2010). Dynamic Discovery of Fuzzy Functional Dependencies Using Partitions. Intelligent Soft Computation and Evolving Data Mining: Integrating Advanced Technologies, 44.Google Scholar
  11. 11.
    Yao, Y.Y., (2003). Information-Theoretic Measures For Knowledge Discovery and Data Mining. Entropy Measures, Maximum Entropy Principle Emerging Applications, 119: 115-136.Google Scholar
  12. 12.
    Zadeh, L.A., (1965). Fuzzy sets. Information and control, 8(3), 338–353. http://wordnet.princeton.edu, 2009
  13. 13.

Copyright information

© Springer India 2014

Authors and Affiliations

  1. 1.Department of CSE and ITCoimbatore Institute of TechnologyCoimbatoreIndia
  2. 2.Sri Ranganathan Institute of Engineering and TechnologyCoimbatoreIndia

Personalised recommendations