Journal of Intelligence and Information Systems (지능정보연구)

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

DOI QR Code

A Hybrid Recommender System based on Collaborative Filtering with Selective Use of Overall and Multicriteria Ratings

종합 평점과 다기준 평점을 선택적으로 활용하는 협업필터링 기반 하이브리드 추천 시스템

  • Received : 2017.11.04
  • Accepted : 2017.12.04
  • Published : 2018.06.30
Download PDF
⟨ Previous Next ⟩

Abstract

Recommender system recommends the items expected to be purchased by a customer in the future according to his or her previous purchase behaviors. It has been served as a tool for realizing one-to-one personalization for an e-commerce service company. Traditional recommender systems, especially the recommender systems based on collaborative filtering (CF), which is the most popular recommendation algorithm in both academy and industry, are designed to generate the items list for recommendation by using 'overall rating' - a single criterion. However, it has critical limitations in understanding the customers' preferences in detail. Recently, to mitigate these limitations, some leading e-commerce companies have begun to get feedback from their customers in a form of 'multicritera ratings'. Multicriteria ratings enable the companies to understand their customers' preferences from the multidimensional viewpoints. Moreover, it is easy to handle and analyze the multidimensional ratings because they are quantitative. But, the recommendation using multicritera ratings also has limitation that it may omit detail information on a user's preference because it only considers three-to-five predetermined criteria in most cases. Under this background, this study proposes a novel hybrid recommendation system, which selectively uses the results from 'traditional CF' and 'CF using multicriteria ratings'. Our proposed system is based on the premise that some people have holistic preference scheme, whereas others have composite preference scheme. Thus, our system is designed to use traditional CF using overall rating for the users with holistic preference, and to use CF using multicriteria ratings for the users with composite preference. To validate the usefulness of the proposed system, we applied it to a real-world dataset regarding the recommendation for POI (point-of-interests). Providing personalized POI recommendation is getting more attentions as the popularity of the location-based services such as Yelp and Foursquare increases. The dataset was collected from university students via a Web-based online survey system. Using the survey system, we collected the overall ratings as well as the ratings for each criterion for 48 POIs that are located near K university in Seoul, South Korea. The criteria include 'food or taste', 'price' and 'service or mood'. As a result, we obtain 2,878 valid ratings from 112 users. Among 48 items, 38 items (80%) are used as training dataset, and the remaining 10 items (20%) are used as validation dataset. To examine the effectiveness of the proposed system (i.e. hybrid selective model), we compared its performance to the performances of two comparison models - the traditional CF and the CF with multicriteria ratings. The performances of recommender systems were evaluated by using two metrics - average MAE(mean absolute error) and precision-in-top-N. Precision-in-top-N represents the percentage of truly high overall ratings among those that the model predicted would be the N most relevant items for each user. The experimental system was developed using Microsoft Visual Basic for Applications (VBA). The experimental results showed that our proposed system (avg. MAE = 0.584) outperformed traditional CF (avg. MAE = 0.591) as well as multicriteria CF (avg. AVE = 0.608). We also found that multicriteria CF showed worse performance compared to traditional CF in our data set, which is contradictory to the results in the most previous studies. This result supports the premise of our study that people have two different types of preference schemes - holistic and composite. Besides MAE, the proposed system outperformed all the comparison models in precision-in-top-3, precision-in-top-5, and precision-in-top-7. The results from the paired samples t-test presented that our proposed system outperformed traditional CF with 10% statistical significance level, and multicriteria CF with 1% statistical significance level from the perspective of average MAE. The proposed system sheds light on how to understand and utilize user's preference schemes in recommender systems domain.

추천시스템은 사용자의 과거 구매행동을 통해 향후 구매할 것이라고 예상되는 제품을 자동으로 검색하여 추천해준다. 특히 전자상거래 기업의 상품추천시스템은 일대일 마케팅의 대표적 실현수단으로 가치가 있다. 하지만, 전통적인 추천시스템, 특히 학계 및 산업계에서 가장 널리 사용되고 있는 전통적인 협업필터링 기법은 단일차원의 '종합 평점'만을 고려하여 추천결과를 생성하도록 설계되어 있어, 사용자들의 정확한 니즈를 이해하고 대응하는데 근본적인 한계가 있다. 최근에는 전자 상거래 기업들도 고객들로부터 보다 다각화된, 다기준 방식으로 피드백을 받고 있다. 특히 다기준 평점은 정량적으로 입력되는 정보이므로 상대적으로 분석 및 처리가 용이하다는 장점이 있다. 그러나 다기준 평점 역시 사전에 정해진 기준에 대해서만 사용자의 피드백이 이루어지기 때문에, 보다 상세하게 사용자의 의견을 이해하여 추천에 반영하는 데에는 한계가 있다. 이에 본 연구는 다기준 평점 정보와 선택적 협업필터링의 서로 다른 접근방법을 통해 도출된 추천결과를 종합하여, 최종적으로 추천 대상리스트를 산출할 수 있는 하이브리드 기술을 제안한다. 본 연구에서 제안한 연구모형의 유용성을 검증하기 위해, 식음료점(식당, 카페 등)에 대한 실제 이용자를 대상으로 온라인 설문을 통해 종합 평점과 다기준 평점을 수집하였으며, 데이터를 학습용과 검증용으로 구분하여 학습시키고 성과를 평가하였다. 이 기법은 결합 함수 기반 접근법과 사용자마다 구매의사결정의 체계가 다르다는 전제하에, 사용자들을 유형화하고, 유형에 따라 정보원을 선택적으로 활용하는 협업필터링 알고리즘을 활용했다. 실험결과, 제안 알고리즘을 통한 추천 방법이 단일 차원을 고려하는 전통적인 협업필터링과 비교해 더 우수한 예측정확도를 나타냄을 확인했다. 아울러, 본 연구가 제안하는 다기준 평점과 선택적 협업필터링 알고리즘을 종합하여 추천하는 방법이, 단순히 다기준 평점을 고려했을 때 보다 통계적으로 유의한 수준의 정확도의 개선이 이루어짐을 확인할 수 있었다.

Keywords

References

  1. Adomavicius, G., R. Sankaranarayanan, S. Sen, and A. Tuzhilin, "Incorporating Contextual Information in Recommender Systems Using a Multidimensional Approach," ACM Transactions on Information Systems, Vol. 23, No. 1(2005), 103-145. https://doi.org/10.1145/1055709.1055714
  2. Adomavicius, G. and Y. Kwon, "New recommendation techniques for multicriteria rating systems," IEEE Intelligent Systems, Vol. 22(2007), 48-55. https://doi.org/10.1109/MIS.2007.58
  3. Adomavicius, G., N. Manouselis, and Y. Kwon, "Multi-criteria Recommender Systems," Recommender Systems Handbook. Springer(2011), 769-803.
  4. Ahn, H., I. Han, and K. -J. Kim, "The Product Recommender System Combining Association Rules and Classification Models: The Case of G Internet Shopping Mall," Information Systems Review, Vol. 8, No. 1(2006), 181-201.
  5. Ahn, S. -M., I. H. Kim, B. Choi, Y. Cho, E. Kim, and M. -K. Kim, "Understanding the Performance of Collaborative Filtering Recommendation through Social Network Analysis," Journal of Society for e-Business Studies, Vol. 17, No. 2(2012), 129-147. https://doi.org/10.7838/JSEBS.2012.17.2.129
  6. Ahn, H., "Improvement of a Context-aware Recommender System through User's Emotional State Prediction," Journal of Information Technology Applications & Management, Vol. 21, No. 4(2014), 203-223.
  7. Balabanovic, M. and Y. Shohm, "Fab : Content-Based, Collaborative Recommendation," Communications of the ACM, Vol. 40, No. 3(1997), 66-72. https://doi.org/10.1145/245108.245124
  8. Breese, J. S., D. Heckerman, and C. Kadie, "Empirical Analysis of Predictive Algorithms for Collaborative Filtering", Proceedings of the 14th Conference on Uncertainty in Artificial Intelligence, UAI-98(1998), 43-52.
  9. Choi, S., K. -Y. Kwahk, and H. Ahn, "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
  10. Haubl, G. and V. Trifts, "Consumer Decision Making in Online Shopping Environments : The Effects of Interactive Decision Aids," Management Science, Vol. 19, No. 1(2000), 4-21.
  11. Heo, Y. -K., J. -S. Oh, P. Paudel, P. Thapa, H. -J. Jeon, M. -A, Jeong, S. -R. Lee, "Density Based system for recommendation of Hybrid POI," The Institute of Electronics Engineers of Korea Summer Conference (2015), 1318-1322.
  12. Herlocker, J. L., J. A. Konstan, A. Borchers, and J. Riedl, "An Algorithm Framework for Performing Collaborative Filtering," Proceedings of the 22nd Annual International ACMSIGIR Conference on Research and Development in information Retrieval(1999), 230-237.
  13. Jannach, D., Z. Karakaya, and F. Gedikli, "Accuracy Improvements for Multi-criteria Recommender Systems", Proceedings of the 13th ACM Conference on Electronic Commerce(2012), 674-689.
  14. Jeon, B., and H. Ahn, "A Collaborative Filtering System Combined with Users Review Mining : Application to the Recommendation of Smartphone Apps," Journal of Intelligence and Information Systems, Vol. 21, No. 2(2015), 1-18. https://doi.org/10.13088/jiis.2015.21.2.01
  15. Kermany. N. R., and S. H. Alizadeh, "A hybrid multi-criteria recommender system using ontology and neuro-fuzzy techniques," Electronic Commerce Research and Applications, Vol. 21(2017), 50-64. https://doi.org/10.1016/j.elerap.2016.12.005
  16. Kim, K. -J., and H. Ahn, "Development of Web-based Intelligent Recommender Systems using Advanced Data Mining Techniques", Journal of Information Technology Applications and Management, Vol. 12, No. 3(2005), 42-56.
  17. Kim, J. K., D. H. Ahn, and Y. H. Cho, "A Personalized Recommender System, WebCF-PT: A Collaborative Filtering using Web Mining and Product Taxonomy", Asia Pacific Journal of Information Systems, Vol. 15, No. 1(2005), 63-79.
  18. Kim, K. -J., and H. Ahn, "User-Item Matrix Reduction Technique for Personalized Recommender Systems," Journal of Information Technology Applications & Management, Vol. 16, No.1(2009), 97-113.
  19. 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
  20. 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(1997), 77-87. https://doi.org/10.1145/245108.245126
  21. Li, Q., C. Wang, G. Geng, "Improving personalized services in mobile commerce by a novel multicriteria rating approach," Proceedings of the 17th International Conference on World Wide Web(2008), 1235-1236.
  22. Liu, L., N. Mehandjiev, D. -L. Xu, "Multi-criteria service recommendation based on user criteria preferences," Proceedings of the fifth ACM Conference on Recommender Systems(2011), 77-84.
  23. Nilashi, M., O. bin Ibrahim, N. Ithnin, "Hybrid recommendation approaches for multi-criteria collaborative filtering," Expert Systems with Applications, Vol. 41(2014a), 3879-3900. https://doi.org/10.1016/j.eswa.2013.12.023
  24. Nilashi, M., O. bin Ibrahim, N. Ithnin, "Multi-criteria collaborative filtering with high accuracy using higher order singular value decomposition and Neuro-Fuzzy system," Knowledge-Based Systems, Vol. 60, (2014b), 82-101. https://doi.org/10.1016/j.knosys.2014.01.006
  25. Nilashi, M., D. Jannach, O. bin Ibrahim, N. Ithnin, "Clustering-and regression-based multi-criteria collaborative filtering with incremental updates," Information Science, Vol. 293(2015), 235-250. https://doi.org/10.1016/j.ins.2014.09.012
  26. Park, M. -H, H. -S. Park, S. -B. Cho, "Restaurant Recommendation for Group of People in Mobile Environments Using Probabilistic Multi-criteria Decision Making," Proceedings of the 8th Asia-Pacific conference on Computer-Human Interaction, Springer Verlag(2008), 114-122.
  27. Park, K.-S. and N. Moon, "Multidimensional Optimization Model of Music Recommender Systems," KIPS Transactions on Computer and Communication Systems, Vol. 19, No. 3(2012), 155-164.
  28. Pazzani, M. J., "A framework for collaborative, content-based and demographic filtering', Artificial Intelligence Review, Vol. 13, Nos. 5-6(1999), 393-408. https://doi.org/10.1023/A:1006544522159
  29. Sahoo, N., R. Krishnan, G. Duncan, and J. P. Callan, "Collaborative filtering with multicomponent rating for recommender systems," Proceedings of the sixteenth annual workshop on information technologies and systems, Milwaukee, WI(2006).
  30. Sahoo, N., R. Krishnan, G. Duncan, and J. Callan, "The Halo Effect in Multi-component Ratings and its Implications for Recommender Systems: The case of Yahoo! Movies," Information Systems Research, Vol.23, No. 1(2012), 231-246. https://doi.org/10.1287/isre.1100.0336
  31. Sarwar, B., G. Karypis, J. Konstan, and J. Riedl, "Item-based collaborative filtering recommendation algorithms', Proceeding of the 10th International Conference on World Wide Web(2001), 285-295.
  32. Schafer, J. B., J. A. Konstan, and J. Riedl, "E-Commerce Recommendation Applications," Data Mining and Knowledge Discovery, Vol. 5, No. 1-2(2001), 115-153. https://doi.org/10.1023/A:1009804230409
  33. Si, L., and R. Jin, "Flexible mixture model for collaborative filtering," Proceedings of the Twentieth International Conference on Machine Learning, ICML(2003), 704-711.
  34. Son, J., S. B. Kim, H. Kim, and S. Cho, "Review and Analysis of Recommender systems," Journal of the Korean Institute of Industrial Engineers, Vol. 41, No. 2(2015), 185-208. https://doi.org/10.7232/JKIIE.2015.41.2.185
  35. Zenebe, A., and A. F. Norcio, "Representation, similarity measures and aggregation methods using fuzzy sets for content-based recommender systems," Fuzzy Sets and Systems, Vol. 160(2009), 76-94. https://doi.org/10.1016/j.fss.2008.03.017

Cited by

  1. 딥러닝을 이용한 온라인 리뷰 기반 다속성별 추천 모형 개발 vol.28, pp.1, 2019, https://doi.org/10.5859/kais.2019.28.1.97
  2. A Hybrid Collaborative Filtering-based Product Recommender System using Search Keywords vol.26, pp.1, 2018, https://doi.org/10.13088/jiis.2020.26.1.151
  3. Product Recommendation System based on User Purchase Priority vol.18, pp.1, 2018, https://doi.org/10.6109/jicce.2020.18.1.55
  4. 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
  5. Modeling of Recommendation System Based on Emotional Information and Collaborative Filtering vol.21, pp.6, 2021, https://doi.org/10.3390/s21061997
  6. BERT 기반 감성분석을 이용한 추천시스템 vol.27, pp.2, 2021, https://doi.org/10.13088/jiis.2021.27.2.001