Association Rule Mining to Extract Knowledge from Online Store Transactions of a Turkish Retail Company: A Case Study

Öz

Data mining techniques have been implemented in many fields namely, marketing, insurance, finance, medicine, computer science and many more. In marketing it is used as a tool to cluster and classify customers so that their buying patterns, demographical information, market basket can be analyzed to help the CRM representative and decision makers [1]. In this study online store transactions of multi-branch Turkish Retail Company have been analyzed and many associations rules have been discovered. The analyzed volume of transactions of completed sales exceeds 14000 for a single season. At first data is cleaned from unrelated fields then presented to R studio to implement the Apriori algorithm[2] in order to extract knowledge and obtain association rules between goods. Results are proven be worthy over the conventional methodologies. The extracted data are tested successfully with a sample group of customers to validate the association rules which give unique insights about customer behaviors.

Anahtar Kelimeler

• Association analysis, Apriori Analysis, Data Mining

Kaynakça

1. Timor M. ,EZERCE A. , GURSOY
2. U. T., “Müşteri Profili ve Alişveriş Davranışlarını Belirlemede Kümeleme ve Birliktelik Kuralları Analizi: Perakende sektöründe bir uygulama” , İstanbul Üniversitesi İşletme Fakültesi İşletme İktisadı Enstitüsü Dergisi, February 2011 22 68
3. R. Agrawal, R. Srikant, Fast algorithms for
4. mining association rules, in: Proceedings of the 20th International Conference on Very Large Data Bases, 1994, pp. 487–499
5. J. Singh, H. Ram, Dr. J.S. Sodhi, Improving
6. Efficiency of Apriori Algorithm Using Transaction Reduction International Journal of Scientific and Research Publications, Volume 3, Issue 1, January 2013
7. Cheng-Hsiung Weng, Mining fuzzy
8. specific rare itemsets for education data, Knowledge-Based Systems, Volume 24, Issue 5, July 2011, Pages 697-708, ISSN 0950-7051, http://dx.doi.org/10.1016/j. knosys.2011.02.010.

9. R. Agrawal, T. Imielinski, A. Swami,
10. Mining association rules between sets of items in large databases, in: Proceedings of ACM SIGMOD, 1993, pp. 207–216.
11. Y.L. Chen, C.H. Weng, Mining association
12. rules from imprecise ordinal data, Fuzzy Sets and Systems 159 (4) (2008) 460–474.
13. Y.L. Chen, C.H. Weng, Mining fuzzy
14. association rules from questionnaire data, Knowledge-Based Systems 22 (1) (2009) 46–56.
15. M. Delgado, N. Marin, D. Sanchez, M.A.
16. Vila, Fuzzy association rules: general model and applications, IEEE Transactions on Fuzzy Systems 11 (2) (2003) 214–225
17. S. S. Weng, S. C. Liu, T. H. Wu, Applying
18. bayesian network and association rule analysis for product recommendation, International Journal of Electronic Business Management 2011
19. Moon, T.K., “The expectation
20. maximization algorithm,” Signal Processing Magazine, IEEE , vol.13, no.6, pp.47,60, Nov 1996 doi: 10.1109/79.543975
21. G. Gürgen, “Birliktelik kuralları ve sepet
22. analizi uygulaması”, yüksek lisans tezi, Marmara Universitesi, istatistik Anabilim dalı
23. T. SERVİ, “Çok Değişkenli Karma
24. Dağilim Modeline Dayali Kümeleme Analizi”, Çukurova Üniversitesi Fen Bilimleri Enstitüsü, PhD. Thesis, 2009