基于隐式反馈数据的个性化游戏推荐

doi:10.3969/j.issn.0372-2112.2018.11.009

电子学报 ›› 2018, Vol. 46 ›› Issue (11): 2626-2632.DOI: 10.3969/j.issn.0372-2112.2018.11.009

基于隐式反馈数据的个性化游戏推荐

俞东进¹, 陈聪¹, 吴建华², 陈耀旺¹

1. 杭州电子科技大学计算机学院, 浙江杭州 310018;
2. 杭州顺网科技股份有限公司, 浙江杭州 310012

收稿日期:2017-09-09 修回日期:2018-03-03 出版日期:2018-11-25
- 作者简介:
- 俞东进 男,生于浙江平湖.博士,教授,研究方向为大数据商务智能、软件仓库分析、服务计算等.E-mail:yudj@hdu.edu.cn;陈聪男,生于浙江温州.硕士研究生,研究方向为推荐系统.E-mail:chencong6837@foxmail.com
- 基金资助:
- 国家自然科学基金 (No.61472112）; 浙江省科技计划项目 (No.2017C01010，No.2016C33170）

Personalized Game Recommendation Based on Implicit Feedback

YU Dong-jin¹, CHEN Cong¹, WU Jian-hua², CHEN Yao-wang¹

1.College of Computer Science and Technology, Hangzhou Dianzi University, Hangzhou, Zhejiang 310018, China;
2.Hangzhou Shunwang Technology Co., Ltd., Hangzhou, Zhejiang 310012, China

Received:2017-09-09 Revised:2018-03-03 Online:2018-11-25 Published:2018-11-25
- Supported by:
- National Natural Science Foundation of China (No.61472112); Science and Technology Project of Zhejiang Province (No.2017C01010, No.2016C33170)

摘要/Abstract

摘要： 现有推荐系统通常采用评分、评论等显式反馈数据实现个性化推荐.然而，显式反馈数据由于在实际中难以获取或因质量问题而往往变得不可用，从而导致相关推荐算法的应用范围受到很大限制.与此相反，诸如点击行为、浏览记录等隐式反馈数据在现实中大量存在.本文提出了一种面向游戏玩家的基于隐式反馈数据的游戏推荐方法.该方法综合考虑了玩家操作次数、操作时长等隐式反馈数据及其时效性，构建了基于伪评分的玩家对游戏的偏好模型，而后通过改进了的SVD++（Singular Value Decomposition++）算法实现个性化游戏推荐.在大规模真实数据集上的实验结果表明本文提出的方法具有更高的推荐精确率和召回率.

关键词: 推荐系统, 隐式反馈, 游戏推荐, 伪评分, SVD++

Abstract: The existing recommendation systems typically employ explicit feedbacks, such as ratings and reviews, to achieve personalized recommendations. However, since the explicit feedbacks are hard to obtain in practice or have poor quality, their applications in the recommendation field are limited. In contrast, implicit feedbacks such as click behaviors and browsing histories are widely available in reality. A game recommendation method based on implicit feedbacks is presented, to provide the personalized game recommendation for game players. This method integrates the time-based implicit feedbacks, such as the times and duration of user operations, and constructs the player's preference model based on the pseudo rating. Meanwhile, it gives the personalized game recommendation by the improved SVD + + (Singular Value Decomposition + +) algorithm. The extensive results of the experiment based on the real data set show that the proposed method has the higher precision and recall.

Key words: recommendation system, implicit feedback, game recommendation, pseudo rating, singular value decomposition + + (SVD + +)

中图分类号:

TP302

俞东进, 陈聪, 吴建华, 等. 基于隐式反馈数据的个性化游戏推荐[J]. 电子学报, 2018, 46(11): 2626-2632.

YU Dong-jin, CHEN Cong, WU Jian-hua, et al. Personalized Game Recommendation Based on Implicit Feedback[J]. Acta Electronica Sinica, 2018, 46(11): 2626-2632.

参考文献

[1] Billsus D,Pazzani M J.Learning collaborative information filters[A].Proceedings of the 15th International Conference on Machine Learning[C].Madison:ICML,1998.46-54.
[2] Koren Y.Factorization meets the neighborhood:a multifaceted collaborative filtering model[A].Proceedings of the 14th International Conference on Knowledge Discovery and Data Mining[C].Las Vegas:ACM,2008.426-434.
[3] Koren Y.Collaborative filtering with temporal dynamics[J].Communications of the ACM,2010,53(4):89-97.
[4] Yang B,Lei Y,Liu J,et al.Social collaborative filtering by trust[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2017,39(8):1633-1647.
[5] 俞春花,刘学军,等.基于上下文相似度和社会网络的移动服务推荐方法[J].电子学报,2017,45(6):1530-1536. YU Chun-hua,LIU Xue-jun,et al.Mobile service recommendation based on context similarity and social network[J].Acta Electronica Sinca,2017,45(6):1530-1536.(in Chinese)
[6] 王俊,李石君,等.一种新的用于跨领域推荐的迁移学习模型[J].计算机学报,2017,40(10):2367-2380. WANG Jun,LI Shi-jun,et al.A new transfer learning model for cross-domain recommendation[J].Chinese Journal of Computer,2017,40(10):2367-2380.(in Chinese)
[7] Pan R,Zhou Y,Cao B,et al.One-class collaborative filtering[A].Proceedings of the 8th IEEE International Conference on Data Mining[C].Pisa:IEEE,2008.502-511.
[8] Li Y,Hu J,Zhai C X,et al.Improving one-class collaborative filtering by incorporating rich user information[A].Proceedings of the 19th ACM International Conference on Information and Knowledge Management[C].Toronto:ACM,2010.959-968.
[9] Pan W,Chen L.GBPR:Group preference based bayesian personalized ranking for one-class collaborative filtering[A].Proceedings of the 23rd International Joint Conference on Artificial Intelligence[C].Beijing:IJCIA,2013.2691-2697.
[10] Hidasi B,Tikk D.Fast ALS-based tensor factorization for context-aware recommendation from implicit feedback[J].Machine Learning and Knowledge Discovery in Databases,2012(2):67-82.
[11] Delporte J,Karatzoglou A,Matuszczyk T,et al.Socially enabled preference learning from implicit feedback data[A].Joint European Conference on Machine Learning and Knowledge Discovery in Databases[C].Berlin:ECML PKDD,2013.145-160.
[12] Hu Y,Koren Y,Volinsky C.Collaborative filtering for implicit feedback datasets[A].Proceedings of the 8th IEEE International Conference on Data Mining[C].Pisa:IEEE,2008.263-2721.
[13] Levandoski J J,Sarwat M,Eldawy A,et al.Lars:A location-aware recommender system[A].IEEE 28th International Conference on Data Engineering[C].Washington:IEEE,2012.450-461.
[14] Yao W,He J,Huang G,et al.A Graph-based model for context-aware recommendation using implicit feedback data[J].World Wide Web,2015,18(5):1351-1371.
[15] Ostuni V C,Di Noia T,Di Sciascio E,et al.Top-n recommendations from implicit feedback leveraging linked open data[A].Proceedings of the 7th ACM Conference on Recommender Systems[C].Hong Kong:ACM,2013.85-92.
[16] Li G,Ou W.Pairwise probabilistic matrix factorization for implicit feedback collaborative filtering[J].Neurocomputing,2016,204:17-25.
[17] Wang S,Huang S,Liu T Y,et al.Ranking-oriented collaborative filtering:A Listwise Approach[J].ACM Transactions on Information Systems,2016,35(2):10.

基于隐式反馈数据的个性化游戏推荐

Personalized Game Recommendation Based on Implicit Feedback

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 15

编辑推荐

Metrics

[1]	曹阳, 高旻, 余俊良, 范琪琳, 荣文戈, 文俊浩. 基于双图混合随机游走的社会化推荐模型[J]. 电子学报, 2023, 51(2): 286-296.
[2]	张帅, 高旻, 文俊浩, 熊庆宇, 唐旭. 基于自监督学习的去流行度偏差推荐方法[J]. 电子学报, 2022, 50(10): 2361-2371.
[3]	郑孝遥, 罗永龙, 汪祥舜, 孙丽萍, 陈付龙, 胡桂银, 汪小寒. 基于位置服务的分布式差分隐私推荐方法研究[J]. 电子学报, 2021, 49(1): 99-110.
[4]	郭景峰, 朱晓松, 李爽. 直播电视推荐系统的评分预测算法研究[J]. 电子学报, 2020, 48(9): 1735-1740.
[5]	黄名选, 蒋曹清. 基于项权值排序挖掘的跨语言查询扩展[J]. 电子学报, 2020, 48(3): 568-576.
[6]	刘露, 胡封晔, 牛亮, 彭涛. 异质网络中基于节点影响力的相似度度量方法[J]. 电子学报, 2019, 47(9): 1929-1936.
[7]	肖云鹏, 孙华超, 戴天骥, 李茜, 李暾. 一种基于云模型的社交网络推荐系统评分预测方法[J]. 电子学报, 2018, 46(7): 1762-1767.
[8]	肖云鹏, 刘晏驰, 刘红, 刘媛妮. 一种基于动态角色标识和张量分解的推荐模型[J]. 电子学报, 2018, 46(3): 569-574.
[9]	黄名选, 蒋曹清. 基于完全加权正负关联模式挖掘的越-英跨语言查询译后扩展[J]. 电子学报, 2018, 46(12): 3029-3036.
[10]	范利云, 左万利, 王英, 王鑫. 一种基于差分隐私和时序的推荐系统模型研究[J]. 电子学报, 2017, 45(9): 2057-2064.
[11]	陈广智, 何文, 李磊. 采用协同过滤技术进行工作流活动推荐[J]. 电子学报, 2017, 45(4): 890-897.
[12]	李改, 陈强, 李磊. 基于评分预测与排序预测的协同过滤推荐算法[J]. 电子学报, 2017, 45(12): 3070-3075.
[13]	黄世平, 黄晋, 陈健, 汤庸. 自动建立信任的防攻击推荐算法研究[J]. 电子学报, 2013, 41(2): 382-387.
[14]	伍之昂, 庄毅, 王有权, 曹杰. 基于特征选择的推荐系统托攻击检测算法[J]. 电子学报, 2012, 40(8): 1687-1693.
[15]	张锋;孙雪冬;常会友;赵淦森. 两方参与的隐私保护协同过滤推荐研究[J]. 电子学报, 2009, 37(1): 84-89.