Journal of Korea Society of Industrial Information Systems (한국산업정보학회논문지)

Korea Society of Industrial Information Systems (한국산업정보학회)
권호 표지
DOI QR코드

DOI QR Code

Game Recommendation System Based on User Ratings

사용자 평점 기반 게임 추천 시스템

  • 김종현 (금오공과대학교 컴퓨터소프트웨어공학과) ;
  • 조현정 (금오공과대학교 컴퓨터소프트웨어공학과) ;
  • 김병만 (금오공과대학교 컴퓨터소프트웨어공학과)
  • Received : 2018.10.04
  • Accepted : 2018.11.06
  • Published : 2018.12.31
Download PDF
⟨ Previous Next ⟩

Abstract

As the recent developments in the game industry and people's interest in game streaming become more popular, non-professional gamers are also interested in games and buying them. However, it is difficult to judge which game is the most enjoyable among the games released in dozens every day. Although the game sales platform is equipped with the game recommendation function, it is not accurate because it is used as a means of increasing their sales and recommending users with a focus on their discount products or new products. For this reason, in this paper, we propose a game recommendation system based on the users ratings, which raises the recommendation satisfaction level of users and appropriately reflect their experience. In the system, we implement the rate prediction function using collaborative filtering and the game recommendation function using Naive Bayesian classifier to provide users with quick and accurate recommendations. As the result, the rate prediction algorithm achieved a throughput of 2.4 seconds and an average of 72.1 percent accuracy. For the game recommendation algorithm, we obtained 75.187 percent accuracy and were able to provide users with fast and accurate recommendations.

최근 게임 산업의 발달과 게임 방송에 대한 사람들의 관심이 많아짐에 따라 기존 게이머들이 아닌 사람들도 게임에 관심을 많이 보이고 있고, 게임 구매로 이어지고 있다. 하지만, 일반 사용자가 매일 수십 개씩 발매되는 게임 중에 어떤 게임이 자신이 재밌게 즐길 수 있는 게임인지를 판단하기 어렵다. 따라서 게임 판매 플랫폼에서 게임 추천 기능을 갖추고 있지만 그들의 매출 증가를 위한 수단으로 사용되어 그들의 할인 제품이나 신제품에 초점을 맞춰 추천을 해주기 때문에 추천 시스템의 정확도가 낮다. 이러한 이유 때문에 본 논문에서는 사용자에 대한 추천 만족도를 높이고 사용자 경험을 적절히 반영한, 사용자가 남긴 평점을 기반으로 한 게임 추천 시스템을 구성하였다. 시스템에서는 협력 필터링을 이용한 예상 평가 점수 기능과 나이브 베이지안을 이용한 게임 추천 기능을 구현하여 사용자에게 빠르고 정확한 추천을 할 수 있도록 구현하였다. 결과적으로 예상 평점 알고리즘의 경우 2.4초의 처리 속도와 평균 72.1퍼센트의 정확도를 얻었고, 게임 추천 알고리즘의 경우 75.187퍼센트의 정확도를 얻어 사용자에게 빠르고 정확한 추천 결과를 제시 할 수 있었다.

Keywords

SOJBB3_2018_v23n6_9_f0001.png 이미지

Fig. 1 Metacritic’s Web Page

SOJBB3_2018_v23n6_9_f0002.png 이미지

Fig. 2 Steam’s Web Page

SOJBB3_2018_v23n6_9_f0003.png 이미지

Fig. 3 Diagram of System Operation

SOJBB3_2018_v23n6_9_f0004.png 이미지

Fig. 4 Diagram of System Structure

SOJBB3_2018_v23n6_9_f0005.png 이미지

Fig. 5 Process of Game Recommendation

SOJBB3_2018_v23n6_9_f0006.png 이미지

Fig. 6 Accuarcy by the Number of Neighbor

SOJBB3_2018_v23n6_9_f0007.png 이미지

Fig. 7 MAE by the Number of Neighbor

SOJBB3_2018_v23n6_9_f0008.png 이미지

Fig. 8 Processing Time by the Number of Neighbor

SOJBB3_2018_v23n6_9_f0009.png 이미지

Fig. 9 Accuracy by Period Limit

SOJBB3_2018_v23n6_9_f0010.png 이미지

Fig. 10 MAE by Period Limit

SOJBB3_2018_v23n6_9_f0011.png 이미지

Fig. 11 Processing Time by Period Limit

SOJBB3_2018_v23n6_9_f0012.png 이미지

Fig. 12 Accuracy by Preference Criteria

Table 1 Example of Game Ratings of User A

SOJBB3_2018_v23n6_9_t0001.png 이미지

Table 2 Dataset for Performance Evaluation depending on the Number of Neighbors

SOJBB3_2018_v23n6_9_t0002.png 이미지

Table 3 Dataset for Performance Evaluation depending on the Period Limit

SOJBB3_2018_v23n6_9_t0003.png 이미지

Table 4 Dataset for Naive Bayesian Classification

SOJBB3_2018_v23n6_9_t0004.png 이미지

References

  1. Francesco, R., Lior, R., and Bracha, S., "Introduction to Recommender Systems Handbook," Recommender Systems Handbook, Springer, pp. 1-35, 2011.
  2. Kim, B. M., Li, Q., Kim, S. G., Lim, E. K., and Kim, J. Y., "A New Approach Combining Content - Based Filtering and Collaborative Filtering for Recommender Systems," Journal of KISS : Software and Applications, Vol. 31, No. 3, pp. 332-342, 2004.
  3. Kim, S. Y., Lee, S. H., and Hwang, H. S., "Design and Implementation of Personalized Recommendation System Using AHP and Hybrid Filtering," Journal of the Korea Industrial Information Systems Research, Vol. 17, No. 7, pp. 111-118, 2012. https://doi.org/10.9723/jksiis.2012.17.7.111
  4. Nam, Y. J., Shin, D. I., and Shin, D. K., "Sensor Data Classification Using Naive Bayesian Classifier," Proceedings of Symposium of the Korean Institute of Communications and Information Sciences, pp. 90-91, 2015.
  5. Brent, S., Greg, L., "Two Decades of Recommender Systems at Amazon.com," IEEE Internet Computing, Vol. 21, No. 3, pp. 12-18, 2017. https://doi.org/10.1109/MIC.2017.72
  6. Carlos, A., Gomez, U., Neil, H., "The Netflix Recommender System," ACM Transactions on Management Information Systems, Vol. 6, No. 4, pp. 1-19, 2015.
  7. https://www.metacritic.com/game
  8. https://store.steampowered.com/
  9. Yun, Y. J., Kim, J. H., Jo, H. J., Yun, G. J., Jeong, K. H., Hong, S. P., Kim, B. M., and Le, H. Y., "Game Recommendation System Using Naive Bayesian Classification," Proceedings of KIIT Summer Conference, pp. 185-187, 2018.
  10. Resnick, P., Iacovou, N., Suchak, M., Bergstorm, P. and Riedl, J., "GroupLens: An Open Architecture for Collaborative Filtering of Netnews," Proc. of ACM Conf. on Computer-Supported Cooperative Work, pp. 175-186, 1994.
  11. Bardrul, S., George, K., Joseph, K., and Riedl, J., "Item-based Collaborative Filtering Recommendation Algorithms," Proc. of WWW 10, 2001.
  12. Lee, S. J., "Optimization of the Similarity Measure for User-based Collaborative Filtering Systems," The Journal of Korean Association Of Computer Education, Vol. 19, No. 1, pp. 111-118, 2016.
  13. Hwang, Y. W., Kim, J. H., Kim, B. M., and Lee, H. A., "Game Recommendation System Based on Collaborative Filtering," Proceedings of the 2017 KISS Conference, pp. 1914-1916, 2017.
  14. Lee, S. J. and Lee, S.W., "A Comparison Study on Preference Calculate Methods for Content-Based Recommendation," Proceedings of the 2010 KISS Conference, Vol. 37, No. 2, pp. 222-227, 2010.

Cited by

  1. 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