The Journal of Korean Institute of Communications and Information Sciences (한국통신학회논문지)

The Korean Institute of Commucations and Information Sciences (한국통신학회)
권호 표지
DOI QR코드

DOI QR Code

Case Study of Big Data-Based Agri-food Recommendation System According to Types of Customers

빅데이터 기반 소비자 유형별 농식품 추천시스템 구축 사례

  • Moon, Junghoon (Seoul National University Department of Agricultural Economics and Rural Development) ;
  • Jang, Ikhoon (Seoul National University Department of Agricultural Economics and Rural Development) ;
  • Choe, Young Chan (Seoul National University Department of Agricultural Economics and Rural Development) ;
  • Kim, Jin Gyo (Seoul National University Business School) ;
  • Bock, Gene (Korea Agency of Education, Promotion & Information Service in Food, Agriculture, Forestry & Fisheries)
  • Received : 2015.02.13
  • Accepted : 2015.05.06
  • Published : 2015.05.31
Download PDF
⟨ Previous Next ⟩

Abstract

The Korea Agency of Education, Promotion and Information Service in Food, Agriculture, Forestry and Fisheries launched a public data portal service in January 2015. The service provides customized information for consumers through an agri-food recommendation system built-in portal service. The recommendation system has fallowing characteristics. First, the system can increase recommendation accuracy by using a wide variety of agri-food related data, including SNS opinion mining, consumer's purchase data, climate data, and wholesale price data. Second, the system uses segmentation method based on consumer's lifestyle and megatrends factors to overcome the cold start problem. Third, the system recommends agri-foods to users reflecting various preference contextual factors by using recommendation algorithm, dirichlet-multinomial distribution. In addition, the system provides diverse information related to recommended agri-foods to increase interest in agri-food of service users.

농림수산식품교육문화정보원에서는 2015년 1월부터 공공데이터 포털 서비스를 시작하였으며 포털 내에 구축된 빅데이터 기반 농식품 추천 시스템을 이용한 맞춤소비정보를 제공하고 있다. 추천시스템의 특징은 첫째, SNS오피니언마이닝, 소비자패널의 모든 구매내역 정보, 기후데이터, 도매가격 데이터와 같은 빅데이터의 성격을 가진 농식품분야의 다양한 데이터들을 이용하기 때문에 데이터 양의 관점에서 추천의 정확도를 높일 수 있다. 둘째, 추천시스템 구축 초기에는 사용자 정보 기반 추천이 어려운 한계를 극복할 수 있는 방법으로 식생활 라이프스타일과 메가트렌드 요인을 이용한 소비자 세분화방법을 사용한다. 이는 사용자 개인정보가 없는 상황에서도 다양한 식품 선호를 반영할 수 있도록 하여 추천실패율을 낯춘다. 셋째, 디리슐레-다항분포를 이용하는 추천 알고리즘을 적용하여 다양한 상황적 요인들의 선호가 반영된 농식품 추천이 가능하도록 하였다. 이 외에도 추천 농식품에 대한 SNS 맛집정보와 버즈량, 관련 식재료를 판매하는 주변 소매점 위치 및 가격정보 등 다양한 정보를 제공하여 농식품 분야 정보에 관심을 높일 수 있도록 시스템을 구현하였다.

Keywords

References

  1. EPIS, RFP for research on agri-food public open data and development bigdata business model, pp. 3, 2014.
  2. J. S. Jeong and S. J. Kang "Hybrid food recommendation system using auto-generated user profiles," J. Korean Inst. Intell. Syst., vol. 21, no. 5, pp. 609-617, 2011. https://doi.org/10.5391/JKIIS.2011.21.5.609
  3. H. J. Ahn and J. W. Kim, "Comparison of product and customer feature selection methods for content-based recommendation in internet storefronts," J. KIPS, vol. 13-D, no. 2, pp. 279-286, 2006.
  4. S. I. Lee and S. Y. Lee, "A collaborative filtering-based recommendation system with relative classification and estimation revision based on Time," J. KIIS, vol. 20, no. 2, pp. 189-194, 2010.
  5. Y. J. Lee and K. J. Kim, "Product recommender systems using multi-model ensemble technique," J. KIISS, vol. 19, no. 2, pp. 39-54, 2013.
  6. J. S. Kim, Y. A. Do, J. W. Ryu, and M. W. Kim, "A collaborative recommendation system using neural networks for increment of performance," J. KBS, vol. 1, no. 2, pp. 233- 244, 2001.
  7. C. H. Shin, J. W. Lee, H. N. Yang, and I. Y. Choi, "The research on recommender for new customers using collaborative filtering and social network analysis," J. KIISS, vol. 18, no. 4, pp. 19-42, 2012.
  8. S. J. Park, S. K. Kang, and Y. K. Kim, "A multimedia contents recommendation system using preference transition probability," J. KIIS, vol. 16, no. 2, pp. 164-171, 2006.
  9. S. Y. Oh, Y. H. Oh, S. H. Han, and H. J. Kim, "Broadcast content recommender system based on user's viewing history," J. Korean Soc. of Broadcast Engineers, vol. 17, no. 1, pp. 129-139, 2012.
  10. K. T. Han, M. K. Park, and Y. S. Choi, "Adaptive and collaborative recommendation using content type," J. KIISE : Softw. and Appl., vol. 38, no. 1, pp. 50-56, 2011.
  11. B. H. Oh, J. H. Yang, and H. J. Lee, "A hybrid recommender system based on collaborative filtering with selective utilization of content-based predicted ratings," J. KIISE : Softw. and Appl., vol. 41, no. 4, pp. 289-294, 2014.
  12. J. H. Lee, J. P. Hwang, and E. T. Kim, "A new kernelized approach to recommender system," J. KIIS, vol. 21, no. 5, pp. 624-629, 2011.
  13. D. S. Park, "Improved movie recommendation system based-on personal propensity and collaborative filtering," KIPS Trans. Comput. and Commun. Syst., vol. 2, no. 11, pp. 475-82, 2013. https://doi.org/10.3745/KTCCS.2013.2.11.475
  14. N. K. Kim and S. Y. Lee, "Bayesian network based music recommendation system considering multi-criteria decision making," The J. Digital Policy & Management, vol. 11, no. 3, pp. 345-352, 2013.
  15. T. Ueta, M. Iwakami, and T. Ito, "Implementation of a goal-oriented recipe recommendation system providing nutrition information," in IEEE Int. Conf. TAAI, pp. 183-188, Chung-Li, Nov. 2011.
  16. H. M. Kim, S. M. Rho, and J. K. Hong, "Design and implementation of fuzzy-based menu recommendation system," J. Korea Navig. Inst., vol. 16, no. 6, pp. 1109-1115, 2012. https://doi.org/10.12673/jkoni.2012.16.6.1109
  17. A. S. Khan and A. Hoffmann, "Building a case-based diet recommendation system without a knowledge engineer," Artificial Intell. Med., vol. 27, no. 2, pp. 155-179, 2003. https://doi.org/10.1016/S0933-3657(02)00113-6
  18. H. K. Han and U. H. Suh, "Learning based personalized foods recommendation agent," in Proc. 32th KIPS Conf., vol. 16, no. 2, pp. 313-314, 2009.
  19. M. Phanich, P. Pholkul, and S. Phimoltares. "Food recommendation system using clustering analysis for diabetic patients," in IEEE.Int. Conf. Inf. Sci. and Appl.(ICISA), pp. 1-8, Seoul, 2010.
  20. J. S. Lee and J. C. Lee. "A case based music recommendation system using contextawareness," J. KIISS, vol. 12, no. 3, pp. 111-126, 2006.
  21. S. I. Lee and S. Y. Lee, "A recommendation system using context-based collaborative filtering," J. KIIS, vol. 21, no. 2, pp. 224-229, 2011.
  22. Y. Oh, A. Choi, and W. Woo, "u-BabSang: A context-aware food recommendation system," The J. Supercomputing, vol. 54, no. 1, pp. 61-81, 2010. https://doi.org/10.1007/s11227-009-0314-5
  23. D. M. Blei, A. Y. Ng, and M. I. Jordan, "Latent dirichlet allocation," J. Machine Learning Research, vol. 3, pp. 993-1022, 2003.
  24. S. J. Pyo, E. H. Kim, and M. C. Kim, "Topic modeling based similar user grouping and TV program recommendation for smart," in Proc. Korean Soc. Broadcast Eng. Conf., pp. 116-119, 2012.
  25. T. M. Cho and J. H. Lee, "Latent keyphrase extraction using LDA model," in Proc. KIIS Fall Conf. 2014, vol. 24, no. 2, pp. 125-126, 2014.
  26. E. H. Kim, S. J. Pyo, and M. C. Kim, "Automatic TV program recommendation using LDA based latent topic inference," J. Broadcating Eng., vol. 17, no. 2, pp. 270-283, 2012. https://doi.org/10.5909/JEB.2012.17.2.270
  27. C. Y. Park, J. D. Lee, J. H. Park, and J. H. Lee, "Contents recommendation method using LDA clustering bbased on program synopsis," in Proc. 2013 Conf. HCI Soc. Korea, pp. 618- 621, 2013.
  28. K. S. Kim, H. K. Jeong, H. J. Lee, and H. J. Kim, "Collaborative filtering using topic models for rating based recommender systems," in Proc. Korean Inf. Sci. Soc. Conf., vol. 39, no. 1B, pp. 381-383, 2012.
  29. K. G. Grunert, K. Brunso, and S. Bisp, Food-related life style: Development of a cross-culturally valid instrument for market surveillance, MAPP Arhus, Denmark, Oct. 1993.
  30. K. Brunso and K. G. Grunert, "Cross-cultural similarities and differences in shopping for food," J. Business Research, vol. 42, no. 2, pp. 145-150, 1998. https://doi.org/10.1016/S0148-2963(97)00114-8
  31. K. G. Grunert, T. Perrea, Y. Zhou, G. Huang, B. T. Sorensen, and A. Krystallis, "Is food-related lifestyle(FRL) able to reveal food consumption patterns in non-western cultural environments? its adaptation and application in urban China," Appetite, vol. 56, no. 2, pp. 357-367, 2011. https://doi.org/10.1016/j.appet.2010.12.020
  32. B. D. Jeong and K. Y. Jang, "Model of u-distribution with use RFID/USN," J. Korea Inst. of Maritime Inf. & Commun. Sci., vol. 11, no. 10, pp. 1814-1820, 2007.
  33. D. Y. Kim, J. E. Lee, S. H. Cha, and K. H. Cho, "Design and implementation of a management framework for ubiquitous home networks," J. KICS, vol. 33, no. 5, pp. 275-284, 2008.
  34. H. W. Lee and H. S. Jeong, "Speech recognition system for intelligent home network system," J. KICS, vol. 33, no. 4, pp. 162-167, 2008.
  35. K. H. Chon and H. J. Choi, "A study on ubiquitous psychological state recognition model using bio-signals," J. KICS, vol. 35, no. 2, pp. 232-243, 2010.
  36. R. Burke, "Hybrid recommender systems: Survey and experiments," User modeling and User-Adapted Interaction, vol. 12, no. 4, pp. 331-370, 2002 https://doi.org/10.1023/A:1021240730564

Cited by

  1. LSTM 언어모델 기반 한국어 문장 생성 vol.41, pp.5, 2015, https://doi.org/10.7840/kics.2016.41.5.592
  2. 협업 필터링과 빈발 패턴을 이용한 개인화된 그룹 추천 vol.41, pp.7, 2016, https://doi.org/10.7840/kics.2016.41.7.768
  3. 양액재배를 위한 생육환경 모니터링 및 제어 플랫폼에 관한 연구 vol.41, pp.9, 2016, https://doi.org/10.7840/kics.2016.41.9.1132
  4. 트위터 사용자의 도시 내 활동반경과 거주지역의 탐색: 라스베이거스 사례 vol.42, pp.2, 2015, https://doi.org/10.7840/kics.2017.42.2.505
  5. R시각화로 연구한 유흥업소와 성병 감염자에 관한 상관관계 vol.17, pp.6, 2017, https://doi.org/10.7236/jiibc.2017.17.6.187