DOI QR코드

DOI QR Code

A Study on the Improvement of Recommendation Accuracy by Using Category Association Rule Mining

카테고리 연관 규칙 마이닝을 활용한 추천 정확도 향상 기법

  • Lee, Dongwon (Division of Social Sciences, Hansung University)
  • 이동원 (한성대학교 사회과학부)
  • Received : 2020.04.04
  • Accepted : 2020.05.26
  • Published : 2020.06.30

Abstract

Traditional companies with offline stores were unable to secure large display space due to the problems of cost. This limitation inevitably allowed limited kinds of products to be displayed on the shelves, which resulted in consumers being deprived of the opportunity to experience various items. Taking advantage of the virtual space called the Internet, online shopping goes beyond the limits of limitations in physical space of offline shopping and is now able to display numerous products on web pages that can satisfy consumers with a variety of needs. Paradoxically, however, this can also cause consumers to experience the difficulty of comparing and evaluating too many alternatives in their purchase decision-making process. As an effort to address this side effect, various kinds of consumer's purchase decision support systems have been studied, such as keyword-based item search service and recommender systems. These systems can reduce search time for items, prevent consumer from leaving while browsing, and contribute to the seller's increased sales. Among those systems, recommender systems based on association rule mining techniques can effectively detect interrelated products from transaction data such as orders. The association between products obtained by statistical analysis provides clues to predicting how interested consumers will be in another product. However, since its algorithm is based on the number of transactions, products not sold enough so far in the early days of launch may not be included in the list of recommendations even though they are highly likely to be sold. Such missing items may not have sufficient opportunities to be exposed to consumers to record sufficient sales, and then fall into a vicious cycle of a vicious cycle of declining sales and omission in the recommendation list. This situation is an inevitable outcome in situations in which recommendations are made based on past transaction histories, rather than on determining potential future sales possibilities. This study started with the idea that reflecting the means by which this potential possibility can be identified indirectly would help to select highly recommended products. In the light of the fact that the attributes of a product affect the consumer's purchasing decisions, this study was conducted to reflect them in the recommender systems. In other words, consumers who visit a product page have shown interest in the attributes of the product and would be also interested in other products with the same attributes. On such assumption, based on these attributes, the recommender system can select recommended products that can show a higher acceptance rate. Given that a category is one of the main attributes of a product, it can be a good indicator of not only direct associations between two items but also potential associations that have yet to be revealed. Based on this idea, the study devised a recommender system that reflects not only associations between products but also categories. Through regression analysis, two kinds of associations were combined to form a model that could predict the hit rate of recommendation. To evaluate the performance of the proposed model, another regression model was also developed based only on associations between products. Comparative experiments were designed to be similar to the environment in which products are actually recommended in online shopping malls. First, the association rules for all possible combinations of antecedent and consequent items were generated from the order data. Then, hit rates for each of the associated rules were predicted from the support and confidence that are calculated by each of the models. The comparative experiments using order data collected from an online shopping mall show that the recommendation accuracy can be improved by further reflecting not only the association between products but also categories in the recommendation of related products. The proposed model showed a 2 to 3 percent improvement in hit rates compared to the existing model. From a practical point of view, it is expected to have a positive effect on improving consumers' purchasing satisfaction and increasing sellers' sales.

인터넷이라는 가상 공간을 활용함으로써 물리적 공간의 제약을 갖는 오프라인 쇼핑의 한계를 넘어선 온라인 쇼핑은 다양한 기호를 가진 소비자를 만족시킬 수 있는 수많은 상품을 진열할 수 있게 되었다. 그러나, 이는 역설적으로 소비자가 구매의사결정 과정에서 너무 많은 대안을 비교 평가해야 하는 어려움을 겪게 함으로써 오히려 상품 선택을 방해하는 원인이 되기도 한다. 이런 부작용을 해소하기 위한 노력으로서, 연관 상품 추천은 수많은 상품을 다루는 온라인 상거래에서 소비자의 구매의사결정 과정 중 정보탐색 및 대안평가에 소요되는 시간과 노력을 줄여주고 이탈을 방지하며 판매자의 매출 증대에 기여할 수 있다. 연관 상품 추천에 사용되는 연관 규칙 마이닝 기법은 통계적 방법을 통해 주문과 같은 거래 데이터로부터 서로 연관성 높은 상품을 효과적으로 발견할 수 있다. 하지만, 이 기법은 거래 건수를 기반으로 하므로, 잠재적으로 판매 가능성이 높을지라도 충분한 거래 건수가 확보되지 못한 상품은 추천 목록에서 누락될 수 있다. 이렇게 추천 시 제외된 상품은 소비자에게 구매될 수 있는 충분한 기회를 확보하지 못할 수 있으며, 또 다시 다른 상품에 비해 상대적으로 낮은 추천 기회를 얻는 악순환을 겪을 수도 있다. 본 연구는 구매의사결정이 결국 상품이 지닌 속성에 대한 사용자의 평가를 기반으로 한다는 점에 착안하여, 추천 시 상품의 속성을 반영하면 소비자가 특정 상품을 선택할 확률을 좀더 정확하게 예측할 수 있다는 점을 추천 시스템에 반영하기 위한 목적으로 수행되었다. 즉, 어떤 상품 페이지를 방문한 소비자는 그 상품이 지닌 속성들에 어느 정도 관심을 보인 것이며 추천 시스템은 이런 속성들을 기반으로 연관성을 지닌 상품을 더 정교하게 찾을 수 있다는 것이다. 상품의 주요 속성의 하나로서, 카테고리는 두 상품 간에 아직 드러나지 않은 잠재적인 연관성을 찾기에 적합한 대상이 될 수 있다고 판단하였다. 본 연구는 연관 상품 추천에 상품 간의 연관성뿐만 아니라 카테고리 간의 연관성을 추가로 반영함으로써 추천의 정확도를 높일 수 있는 예측모형을 개발하였고, 온라인 쇼핑몰로부터 수집된 주문 데이터를 활용하여 이루어진 실험은 기존 모형에 비해 추천 성능이 개선됨을 보였다. 실무적인 관점에서 볼 때, 본 연구는 소비자의 구매 만족도를 향상시키고 판매자의 매출을 증가시키는 데에 기여할 수 있을 것으로 기대된다.

Keywords

References

  1. Agrawal, R., T. Imielinski, A. Swami. "Mining association rule between sets of items in large databases," Proc. 1993 ACM SIGMOD international conference on management of data, (1993), 207-216.
  2. Adomavicius, G., A. Tuzhilin. "Context-Aware Recommender Systems. Recommender Systems Handbook, Springer US, (2011), 217-253.
  3. Aljukhadar, Muhammad, Sylvain Senecal, and Charles-Etienne Daoust. "Using recommendation agents to cope with information overload." International Journal of Electronic Commerce Vol.17, No.2(2012), 41-70. https://doi.org/10.2753/JEC1086-4415170202
  4. Anand, S.S., A.R. Patrick. "A Data Mining methodology for cross-sales," Knowledge-Based Systems, Vol.10, No.7(1998), 449-461. https://doi.org/10.1016/S0950-7051(98)00035-5
  5. Ansari, A., S. Essegaier, R. Kohli. "Internet recommender systems," Journal of Marketing Research, Vol.37, No.3(2000), 363-375. https://doi.org/10.1509/jmkr.37.3.363.18779
  6. Balabanovic, M., Y. Shoham. "Content-Based, Collaborative Recommendation," Communications of the ACM, Vol.40, No.3(1997), 66-72. https://doi.org/10.1145/245108.245124
  7. Bodapati, A.V. "Recommender systems with purchase data," Journal of Marketing Research, Vol.45, No.1(2008), 77-93. https://doi.org/10.1509/jmkr.45.1.77
  8. Chen, Y.L., J.M. Chen, C.W. Tung. "A data mining approach for retail knowledge discovery with consideration of the effect of shelf-space adjacency on sales," Decision Support Systems, Vol.42, No.3(2006), 1503-1520. https://doi.org/10.1016/j.dss.2005.12.004
  9. Chernev, Alexander, Ulf Bockenholt, and Joseph Goodman. "Choice overload: A conceptual review and meta-analysis." Journal of Consumer Psychology, Vol.25, No.2 (2015), 333-358. https://doi.org/10.1016/j.jcps.2014.08.002
  10. Choi, S., Hyun, Y., Kim, N. "Improving Performance of Recommendation Systems Using Topic Modeling," Journal of Intelligence and Information Systems, Vol.21, No.3(2015), 101-116. https://doi.org/10.13088/jiis.2015.21.3.101
  11. Choi, S., Kwahk, K.-Y., Ahn, H. "Enhancing Predictive Accuracy of Collaborative Filtering Algorithms using the Network Analysis of Trust Relationship among Users," Journal of Intelligence and Information Systems, Vol.22, No.3(2016), 113-127. https://doi.org/10.13088/jiis.2016.22.3.113
  12. Fleder, D., K. Hosanagar. "Blockbuster culture's next rise or fall: The impact of recommender systems on sales diversity," Management Science, Vol.55, No.5(2009), 697-712. https://doi.org/10.1287/mnsc.1080.0974
  13. Kim, B. K., S. Lee, S. Bang, J. Kim, and J. H. Lee, "Personalized Recommendation System Using Social Network," Proceedings of the Conference on Intelligent Information Systems, Vol.20, No.1(2010), 48-49.
  14. Kim, J., Lee, S.-W. "The Ontology Based, the Movie Contents Recommendation Scheme, Using Relations of Movie Metadata," Journal of Intelligence and Information Systems, Vol.19, No.3(2013), 25-44. https://doi.org/10.13088/jiis.2013.19.3.025
  15. Kim, K.-J., Kim, B.-G. "Product Recommender System for Online Shopping Malls using Data Mining Techniques," Journal of Intelligence and Information Systems, Vol.11, No.1(2005), 191-205.
  16. Kim, M., and K. J. Kim, "Recommender Systems using Structural Hole and Collaborative Filtering," Journal of Intelligence and Information Systems, Vol.20, No.4(2014), 107-120. https://doi.org/10.13088/jiis.2014.20.4.107
  17. Kim, M. G., and K. J. Kim, " Recommender Systems using SVD with Social Network Information," Journal of Intelligence and Information Systems, Vol.22, No.4(2016), 1-18. https://doi.org/10.13088/jiis.2016.22.4.001
  18. Kim, S. H., and R. S. Chang, "The Study on the Research Trend of Social Network Analysis and the its Applicability to Information Science," Journal of the Korean Society for Information Management, Vol.27, No.4(2010), 71-87. https://doi.org/10.3743/KOSIM.2010.27.4.071
  19. Kim, Y., and W.N. Street. "An intelligent system for customer targeting: a data mining approach," Decision Support Systems, Vol.37, No.2(2004), 215-228. https://doi.org/10.1016/S0167-9236(03)00008-3
  20. Konstan, J.A., B.N. Miller, D. Maltz, J.L. Herlocker, L.R. Gordon, J. Riedl. "GroupLens: applying collaborative filtering to Usenet news," Communications of the ACM, Vol.40, No.3(1997), 77-87. https://doi.org/10.1145/245108.245126
  21. Lee, D. "A Regression-Model-based Method for Combining Interestingness Measures of Association Rule Mining." Journal of Intelligence and Information Systems, Vol.23, No.1(2017), 127-141. https://doi.org/10.13088/jiis.2017.23.1.127
  22. Lee, D. "Extension Method of Association Rules Using Social Network Analysis." Journal of Intelligence and Information Systems, Vol.23, No.4 (2017), 111-126. https://doi.org/10.13088/JIIS.2017.23.4.111
  23. Lee, D., S. Park, S. Moon. "Utility-based association rule mining: A marketing solution for cross-selling," Expert Systems with Applications. Vol.40, No.7(2013), 2715-2725. https://doi.org/10.1016/j.eswa.2012.11.021
  24. Scheibehenne, Benjamin, Rainer Greifeneder, and Peter M. Todd. "Can there ever be too many options? A meta-analytic review of choice overload." Journal of consumer research Vol.37, No.3(2010), 409-425. https://doi.org/10.1086/651235
  25. Shin, C. H., J. W. Lee, H. N. Yang, and I. Y. Choi, "The Research on Recommender for New Customers Using Collaborative Filtering and Social Network Analysis," Journal of Intelligence and Information Systems, Vol.18, No.4(2012), 19-42. https://doi.org/10.13088/JIIS.2012.18.4.019