Journal of Intelligence and Information Systems (지능정보연구)

Korea Intelligent Information System Society (한국지능정보시스템학회)
권호 표지
DOI QR코드

DOI QR Code

A Study on Improvement of Collaborative Filtering Based on Implicit User Feedback Using RFM Multidimensional Analysis

RFM 다차원 분석 기법을 활용한 암시적 사용자 피드백 기반 협업 필터링 개선 연구

  • 이재성 (과학기술연합대학원대학교 과학기술경영정책학과) ;
  • 김재영 (아주대학교 미디어학부) ;
  • 강병욱 (경기대학교 산업공학과)
  • Received : 2018.06.02
  • Accepted : 2019.01.26
  • Published : 2019.03.31
Download PDF
⟨ Previous Next ⟩

Abstract

The utilization of the e-commerce market has become a common life style in today. It has become important part to know where and how to make reasonable purchases of good quality products for customers. This change in purchase psychology tends to make it difficult for customers to make purchasing decisions in vast amounts of information. In this case, the recommendation system has the effect of reducing the cost of information retrieval and improving the satisfaction by analyzing the purchasing behavior of the customer. Amazon and Netflix are considered to be the well-known examples of sales marketing using the recommendation system. In the case of Amazon, 60% of the recommendation is made by purchasing goods, and 35% of the sales increase was achieved. Netflix, on the other hand, found that 75% of movie recommendations were made using services. This personalization technique is considered to be one of the key strategies for one-to-one marketing that can be useful in online markets where salespeople do not exist. Recommendation techniques that are mainly used in recommendation systems today include collaborative filtering and content-based filtering. Furthermore, hybrid techniques and association rules that use these techniques in combination are also being used in various fields. Of these, collaborative filtering recommendation techniques are the most popular today. Collaborative filtering is a method of recommending products preferred by neighbors who have similar preferences or purchasing behavior, based on the assumption that users who have exhibited similar tendencies in purchasing or evaluating products in the past will have a similar tendency to other products. However, most of the existed systems are recommended only within the same category of products such as books and movies. This is because the recommendation system estimates the purchase satisfaction about new item which have never been bought yet using customer's purchase rating points of a similar commodity based on the transaction data. In addition, there is a problem about the reliability of purchase ratings used in the recommendation system. Reliability of customer purchase ratings is causing serious problems. In particular, 'Compensatory Review' refers to the intentional manipulation of a customer purchase rating by a company intervention. In fact, Amazon has been hard-pressed for these "compassionate reviews" since 2016 and has worked hard to reduce false information and increase credibility. The survey showed that the average rating for products with 'Compensated Review' was higher than those without 'Compensation Review'. And it turns out that 'Compensatory Review' is about 12 times less likely to give the lowest rating, and about 4 times less likely to leave a critical opinion. As such, customer purchase ratings are full of various noises. This problem is directly related to the performance of recommendation systems aimed at maximizing profits by attracting highly satisfied customers in most e-commerce transactions. In this study, we propose the possibility of using new indicators that can objectively substitute existing customer 's purchase ratings by using RFM multi-dimensional analysis technique to solve a series of problems. RFM multi-dimensional analysis technique is the most widely used analytical method in customer relationship management marketing(CRM), and is a data analysis method for selecting customers who are likely to purchase goods. As a result of verifying the actual purchase history data using the relevant index, the accuracy was as high as about 55%. This is a result of recommending a total of 4,386 different types of products that have never been bought before, thus the verification result means relatively high accuracy and utilization value. And this study suggests the possibility of general recommendation system that can be applied to various offline product data. If additional data is acquired in the future, the accuracy of the proposed recommendation system can be improved.

전자상거래 시장의 이용이 보편화 되며 고객들에게 좋은 품질의 물건을 어디서, 얼마나 합리적으로 구매할 수 있는지가 중요해졌다. 이러한 구매 심리의 변화는 방대한 정보 속에서 오히려 고객들의 구매 의사결정을 어렵게 만드는 경향이 있다. 이때 추천 시스템은 고객의 구매 행동을 분석하여 정보 검색에 드는 비용을 줄이고 만족도를 높이는 효과가 있다. 하지만 대부분 추천 시스템은 책이나 영화 등 동종 상품 분류 내에서만 추천이 이뤄진다. 왜냐하면 추천 시스템은 특정 상품에 매긴 구매 평점 데이터를 기반으로 해당 상품 분류 내 유사한 상품에 대한 구매 만족도를 추정하기 때문이다. 그밖에 추천 시스템에서 사용하는 구매 평점의 신뢰성에 대한 문제도 제시되고 있으며 오프라인에선 평점 확보 자체가 어렵다. 이에 본 연구에서는 일련의 문제를 개선하기 위해 RFM 다차원 분석 기법을 활용하여 기존에 사용하던 고객의 구매 평점을 객관적으로 대체할 수 있는 새로운 지표의 활용 가능성을 제안하는 바이다. 실제 기업의 구매 이력 데이터에 해당 지표를 적용해서 검증해본 결과 높게는 약 55%에 해당하는 정확도를 기록했다. 이는 총 4,386종에 달하는 이종 상품들 중 한번도 이용해 본 적 없는 상품을 추천한 결과이기 때문에 검증 결과는 상대적으로 높은 정확도와 활용가치를 의미한다. 그리고 본 연구는 오프라인의 다양한 상품데이터에서도 적용할 수 있는 범용적인 추천 시스템의 가능성을 시사한다. 향후 추가적인 데이터를 확보한다면 제안하는 추천 시스템의 정확도 향상도 기대할 수 있다.

Keywords

JJSHBB_2019_v25n1_139_f0001.png 이미지

Research model Design

JJSHBB_2019_v25n1_139_f0002.png 이미지

Number of customers by age

JJSHBB_2019_v25n1_139_f0003.png 이미지

Percentage of customers by age

JJSHBB_2019_v25n1_139_f0004.png 이미지

Example of RFM score by product (ID 798 in F_elder Group)

JJSHBB_2019_v25n1_139_f0005.png 이미지

Compare result of the Model test

Usage Data and Variable Description

JJSHBB_2019_v25n1_139_t0001.png 이미지

Operational definition of RFM

JJSHBB_2019_v25n1_139_t0002.png 이미지

Example of RFM score(ID 798 in F_elder Group)

JJSHBB_2019_v25n1_139_t0003.png 이미지

Example of recommendation result (F_elder Group)

JJSHBB_2019_v25n1_139_t0004.png 이미지

Validation data set evaluation result

JJSHBB_2019_v25n1_139_t0005.png 이미지

Test data set evaluation result

JJSHBB_2019_v25n1_139_t0006.png 이미지

References

  1. Ahmed, S., J. Kim, and S. Kang, "Enhanced Recommendation Algorithm using Semantic Collaborative Filtering - E-commerce Portal," Journal of Intelligence and Information Systems, Vol.17, No.3(2011), 79-98. https://doi.org/10.13088/JIIS.2011.17.3.079
  2. Ahn, K. C., C. B. Moon, B. M. Kim, S. S. Yoon, and H. S. Kim, "POS Data Analysis System based on Association Rule Analysis," Journal of the Korea industrial information systems society, Vol.17, (2012), 9-17.
  3. Ahn, Y. C., "Implemental Model of Customer Relationship Management System for Oriental Hospital Using Customer Segmentation," Korea Society of Industrial Information Systems, Vol.15, No.5(2010), 79-87.
  4. Amatriain, Xavier, J. M. Pujol, and N. Oliver, "I like it... i like it not: Evaluating user ratings noise in recommender systems," International Conference on User Modeling, Adaptation, and Personalization, (2009), 247-258.
  5. Bellogin, A., A. Said, and A. P. de Vries, "The magic barrier of recommender systems-no magic, just ratings," International Conference on User Modeling, Adaptation, and Personalization, (2014), 25-36.
  6. Chan, C. C. H., "Online auction customer segmentation using a neural network model," International Journal of Applied Science and Engineering, Vol.3, No.2(2005), 101-109.
  7. Chen, P., "Broadvision delivers new frontier for e-commerce." M-commerce. October 25, (2000).
  8. Cheng, C. H. and Y. S. Chen, "Classifying the segmentation of customer value via RFM model and RS theory," Expert systems with applications, Vol.36, No. 3(2009), 4176-4184. https://doi.org/10.1016/j.eswa.2008.04.003
  9. Choi, Y. H., "RFM analysis of Korean professional baseball spectators," Journal of Sport and Leisure Studies, Vol.50, No.1 (2012), 289-299. https://doi.org/10.51979/KSSLS.2012.12.50.289
  10. Choi, Y. K., and S. K. Kim, "Recommendation Algorithms for Online Shopping Malls with Periodically Purchasing Users," Journal of KIISE: Software and Applications, Vol.40, No.8(2013), 453-462.
  11. Claypool, M., A, Gokhale, T. Miranda, P. Murnikov, D. Netes, and M. Sartin, "Combining contents-based and collaborative filters in an online news paper," ACM SIGIR '99 Workshop on Recommender Systems, (1999).
  12. Department of Statistics Korea, "Online shopping 20 years by statistics", 2016. Available at http://kostat.go.kr/portal/korea/kor_nw/2/1/index.board?bmode=read&aSeq=354647/ (Downloaded 15 March, 2018).
  13. Forrester Research, "Forrester Research 2011 Annual Report", 2011. Available at http://phx.corporate-ir.net/phoenix.zhtml?c=60569&p=irol-reportsannual/ (Downloaded 13 March, 2018)
  14. Goldberg, K., D. Gupta, M. Digiovanni, and H. Narita, "Jester 2.0: Evaluation of a new linear time collaborative filtering algorithm," Intl. ACM SIGIR Conf. on Research and Development in Information Retrieval, (1999)
  15. Good, N., J. B. Schafer, J. A. Konstan, A. borchers, B. Sarwa, J. Herlocker, and J. Ridel, "Combining collaborative filtering with personal agents for better recommenations," Proceedings of the Sixteenth National Conference on Artificial Intelligenc, (1999), 439-446.
  16. Ha, S. H. and K. H. Baek, "Analyzing Customer Purchase Behavior of a Department Store and Applying Customer Relationship Management Strategies," Korean Management Science Review, Vol.21, No.3(2004), 55-69.
  17. Harper, F. M., X. Li, Y. Chen, and J. A. Konstan, "An economic model of user rating in an online recommender system," International Conference on User Modeling, (2005), 307-316.
  18. Herlocker, J. L., J. A. Konstan, L. G. Terveen, and J. T. Riedl, "Evaluating collaborative filtering recommender systems," ACM Transactions on Information Systems (TOIS), Vol.22, No.1 (2004), 5-53. https://doi.org/10.1145/963770.963772
  19. Hsieh, N. C., "An integrated data mining and behavioral scoring model for analyzing bank customers," Expert Systems with Applications, Vol.27, No.4(2004), 623-633. https://doi.org/10.1016/j.eswa.2004.06.007
  20. Hughes, A. M., Strategic database marketing, Probus Publishing Company, 1994.
  21. Jeong, Y. J., I. Y., Choi, J. K. Kim, and J. C. Choi, "Strategy for Store Management Using SOM Based on RFM," Journal of Intelligence and Information Systems, Vol.21, No.2(2015), 93-112. https://doi.org/10.13088/jiis.2015.21.2.93
  22. Kim, J. H., K. H. Lee, H. J. Lee, and D. S. Park, "Development of Recommendation System based on Data Mining Technique for E-Commerce," Journal of Korean Institute of Information Technology, Vol.2, No.1(2004), 47-57.
  23. Kim, J. H., K. C. Nam, and S. J. Lee, "Forecasting of Customer's Purchasing Intention Using Support Vector Machine," Information Systems Review, Vol.10, No.2(2008), 137-158.
  24. Kim, J. H., B. H. Ahn, and D. Jeong, "A Recommender System using Mixed Filtering for Health Products," The Journal of Internet Electronic Commerce Research, Vol.12, No.2 (2016), 109-124.
  25. Kim, J. W., S. J. Bae, and H. J. Lee, "Sparsity Effect on Collaborative Filtering-based Personalized Recommendation," Asia Pacific Journal of Information Systems, Vol.14, No.2 (2004), 131-149. https://doi.org/10.1111/j.1365-2575.2004.00167.x
  26. Kim, Y., and S. B. Moon, "A Study on Hybrid Recommendation System Based on Usage Frequency for Multimedia Contents," Journal of the Korean Society for Information Management, Vol.23, No.3(2006), 91-125. https://doi.org/10.3743/KOSIM.2006.23.3.091
  27. Konstan, J. A, B. N. Miller, D. Maltz, J. L. Herlocker, L. R. Gordon, and J. Riedl, "GroupLens: Applying Collaborative Filtering to Usenet News," Communication of the ACM, Vol.40, No.3(1997), 77-87. https://doi.org/10.1145/245108.245126
  28. Kotler, P., Principles of Marketing (15th Edition), Prentice Hall., p.411.
  29. Kwon, H. J., and K. S. Hong, "Method to Improve Data Sparsity Problem of Collaborative Filtering Using Latent Attribute Preference," Journal of Internet Computing and Services, Vol.14, No.5(2013), 59-67. https://doi.org/10.7472/jksii.2013.14.5.59
  30. Lee, O. J., M. S. Hong, W. J. Lee, and J. D. Lee, "Scalable Collaborative Filtering Technique based on Adaptive Clustering," Journal of Intelligence and Information Systems, Vol.20, No.2(2014), 73-92. https://doi.org/10.13088/jiis.2014.20.2.073
  31. Lee, Y. H., U. G. Kang, and H. J. Hwang, "Hospital Customer Segmentation Strategies based on RFM Model," Journal of KIISE, Vol.2, No.1(2005), 25-33.
  32. Li, D. K., and B. K. Ha, "Posting RFM Model for Evaluating the Member Loyalty in Social Network Sites," The Society of service Science, Vol.1, No.1(2011), 49-60.
  33. Mackenzie, I., C. Meyer, and S. Nobble, "How retailers can keep up with consumers," McKinsey & Company, 2013. Available at http://www.mckinsey.com/industries/retail/our-insights/how-retailers-can-keep-up-with-consumers (Downloaded 13 March, 2018)
  34. Newell, F., The new rules of marketing: How to use one-to-one relationship marketing to be the leader in your industry, New York: McGraw-Hills Companies Inc., 1997.
  35. Nguyen, T. T., D. Kluver, T.-Y. Wang, P.-M. Hui, M. D. Ekstrand, M. C. Willemsen, and J. Riedl, "Rating support interfaces to improve user experience and recommender accuracy," Paper Presented at the Proceedings of the 7th ACM Conference on Recommender Systems, (2013).
  36. Oard, D. W., and J. Kim, "Implicit feedback for recommender systems," Proceedings of the AAAI workshop on recommender systems, Vol. 83, (1998).
  37. Oh, J. M, and N. M. Moon, "Preference Element Changeable Recommender System based on Extended Collaborative Filtering," Computer and Information-Journal of the Institute of Electronics Engineers of Korea, Vol.47, No.4(2010), 18-24.
  38. Park, D. H., H. K. Kim, I. Y. Choi, and J. K. Kim, "A literature review and classification of recommender systems research," Expert Systems with Applications, Vol.39, No.11 (2012), 10059-10072. https://doi.org/10.1016/j.eswa.2012.02.038
  39. Park, K. H., D. H. Baek, H. C. Jeon, and J. Y. Seo, "Development of a Merchandising Evaluation Framework for Internet Shopping Malls," The Korean Association of Small Business Studies, Vol.27, No.1(2005), 89-114.
  40. Park, Y. J., and K. N. Chang, "A study on the customer behavior based customer profile model for personalized products recommendation," Proceedings of Korean Academic Society Of Business Administration, (2005), 315-322.
  41. Parthasarathy, S., M. J. Zaki, M. Ogihara and S. Dwarkadas, "Incremental and Interactive Sequence Mining," Proceeding of the 8th International Counterenn Information and Knowledge Management (CIKM'99), (1999).
  42. Potoniee, O., "Ubiquitous Personalization: a Smart Card Based Approach," Gemplus Developer Conference, (2002).
  43. Rogers, E. M., The diffusion of innovations, The Tree Press, New York, 1962.
  44. Said, A., B. J. Jain, S. Narr, and T. Plumbaum, "Users and noise: The magic barrier of recommender systems," International Conference on User Modeling, Adaptation, and Personalization, (2012), 237-248.
  45. Shardanand. P, and P. Maes, "Social Information Filtering Algorithms for Automating Word of Month," Proceedings of Conference on Human Factors in Computer Systems, (1995), 210-217.
  46. Wei, J. T., M. C. Lee, H. K. Chen, and H. H. Wu, "Customer relationship management in the hairdressing industry: An application of data mining techniques," Expert Systems with Application, Vol.40, No.18(2013), 7513-7518. https://doi.org/10.1016/j.eswa.2013.07.053
  47. Wu, J., and Z. Lin, "Research on customer segmentation model by clustering," Proceedings of the 7th international conference on Electronic commerce, (2005), 316-318.
  48. Yu, S. J., "A Study of Improvement of Individual Item Diversity in Collaborative Filtering-based Recommendation," Journal of Korean Institute of Information Technology, Vol.14, No.8(2016), 89-64.
  49. Yun, S., and H. Yoon, "An Analysis of Performance Improvement Algorithm for Personalized Recommender System," Proceedings of KFIS Spring Conference 2005, Vol.15, No.1(2005), 181-184.

Cited by

  1. Sentiment Digitization Modeling for Recommendation System vol.12, pp.12, 2019, https://doi.org/10.3390/su12125191
  2. Improvement of a Product Recommendation Model using Customers' Search Patterns and Product Details vol.26, pp.1, 2021, https://doi.org/10.9708/jksci.2021.26.01.265