Please wait a minute...
浙江大学学报(工学版)  2019, Vol. 53 Issue (9): 1788-1794    DOI: 10.3785/j.issn.1008-973X.2019.09.018
计算机科学与人工智能     
神经协同过滤智能商业选址方法
李诺(),郭斌*(),刘琰,景瑶,於志文
西北工业大学 计算机学院,陕西 西安 710072
Intelligent commercial site recommendation with neural collaborative filtering
Nuo LI(),Bin GUO*(),Yan LIU,Yao JING,Zhi-wen YU
School of Computer Science, Northwestern Polytechnical University, Xi'an 710072, China
 全文: PDF(1041 KB)   HTML
摘要:

为了挖掘商店类别与地址之间的关系,基于神经协同过滤(NCF)框架提出商业选址神经协同过滤方法——NeuMF-RS. 采用嵌入方式分别得到商店类别和地址的表示,利用矩阵分解的思想学习商店类别与地址之间的线性关系;利用深度学习多层感知机学习商店类别与地址之间非线性、深层次的关系;结合这2种方法学习到的关系得到最终结果. 利用北京市的餐馆数据与POI数据来评价NeuMF-RS方法的性能,结果表明,NeuMF-RS相对于其他先进的深度学习方法和协同过滤方法在商业选址方面具有更好的性能,更能兼顾线性与非线性关系.

关键词: 商业选址推荐系统神经协同过滤(NCF)多层感知机矩阵分解    
Abstract:

A new neural collaborative filtering method, NCF-RS, was proposed based on the framework of neural collaborative filtering (NCF). In order to discover the relationship between store category and site, the linear relationship between store categories and sites was studied by matrix decomposition, the non-linear and in-depth relationship between store categories and sites was studied by deep learning multi-layer perceptron, then the two relationships were combined for the final results. Restaurants’ data and POI data in Beijing were used to evaluate the performance of NCF-RS. Results indicate that NCF-RS has better performance in intelligent commercial site recommendation than other advanced deep learning methods and collaborative filtering methods, and can take linear and nonlinear relationships into better consideration.

Key words: commercial site recommendation    recommendation system    neural collaborative filtering (NCF)    multi-layer perceptron    matrix decomposition
收稿日期: 2018-12-17 出版日期: 2019-09-12
CLC:  TP 399  
通讯作者: 郭斌     E-mail: linuo@mail.nwpu.edu.cn;guob@nwpu.edu.cn
作者简介: 李诺(1995—),女,博士生,从事普适计算研究. orcid.org/0000-0003-3569-894X. E-mail: linuo@mail.nwpu.edu.cn
服务  
把本文推荐给朋友
加入引用管理器
E-mail Alert
作者相关文章  
李诺
郭斌
刘琰
景瑶
於志文

引用本文:

李诺,郭斌,刘琰,景瑶,於志文. 神经协同过滤智能商业选址方法[J]. 浙江大学学报(工学版), 2019, 53(9): 1788-1794.

Nuo LI,Bin GUO,Yan LIU,Yao JING,Zhi-wen YU. Intelligent commercial site recommendation with neural collaborative filtering. Journal of ZheJiang University (Engineering Science), 2019, 53(9): 1788-1794.

链接本文:

http://www.zjujournals.com/eng/CN/10.3785/j.issn.1008-973X.2019.09.018        http://www.zjujournals.com/eng/CN/Y2019/V53/I9/1788

图 1  神经协同过滤框架
图 2  基于神经协同过滤的商业选址框架
图 3  基于神经协同过滤改进的NCF-RS模型
图 4  北京市所有餐馆的热力图
图 5  推荐性能HR@10随潜在因子的变化
图 6  推荐性能NDCG@10随潜在因子的变化
图 7  推荐性能HR随推荐列表长度的变化
图 8  推荐性能NDCG随推荐列表长度的变化
1 LIAN J, ZHANG F, XIE X, et al. Restaurant survival analysis with heterogeneous information [C] // Proceedings of the 26th International Conference on World Wide Web Companion. Perth: IW3C2, 2017: 993-1002.
2 ROIG-TIERNO N, BAVIERA-PUIG A, BUITRAGO-VERA J, et al The retail site location decision process using GIS and the analytical hierarchy process[J]. Applied Geography, 2013, 40: 191- 198
doi: 10.1016/j.apgeog.2013.03.005
3 XU M, WANG T, WU Z, et al. Demand driven store site selection via multiple spatial-temporal data [C] // Proceedings of the 24th ACM SIGSPATIAL International Conference on Advances in Geographic Information Systems. Burlingame: ACM, 2016: 40.
4 KARAMSHUK D, NOULAS A, SCELLATO S, et al. Geo-spotting: mining online location-based services for optimal retail store placement [C] // Proceedings of the 19th ACM SIGKDD international conference on Knowledge discovery and data mining. Chicago: ACM, 2013: 793-801.
5 CHEN L, ZHANG D, PAN G, et al. Bike sharing station placement leveraging heterogeneous urban open data [C] // Proceedings of the 2015 ACM International Joint Conference on Pervasive and Ubiquitous Computing. Osaka: ACM, 2015: 571-575.
6 CUO B, LI J, ZHENG V W, et al CityTransfer: Transferring Inter-and Intra-City knowledge for chain store site recommendation based on multi-source urban data[J]. Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies, 2018, 1 (4): 135
7 ZHANG S,YAO L,SUN A X,et al Deep learning based recommender system: a survey and new perspectives[J]. ACM Computing Surveys (CSUR), 2019, 52 (1): 5
8 HE X, LIAO L, ZHANG H, et al. Neural collaborative filtering [C] // Proceedings of the 26th International Conference on World Wide Web Companion. Perth: International World Wide Web Conferences Steering Committee, 2017: 173-182.
9 CHIEN Y H, GEORGE E I. A Bayesian model for collaborative filtering [C] // AISTATS. [S.l.]: [s.n.], 1999.
10 BROWNING J, MILLER D J A maximum entropy approach for collaborative filtering[J]. Journal of VLSI Signal Processing Systems for Signal, Image and Video Technology, 2004, 37 (2/3): 199- 209
doi: 10.1023/B:VLSI.0000027485.11890.15
11 KOREN Y, BWLL R, VOLINSKY C Matrix factorization techniques for recommender systems[J]. Computer, 2009, 42 (8): 30- 37
doi: 10.1109/MC.2009.263
12 TOROSLU ? H. A singular value decomposition approach for recommendation systems [D]. Ankara: METU, 2010: 1-67.
13 SARWAR B, KARYPIS G, KONSTAN J, et al. Item-based collaborative filtering recommendation algorithms [C] // Proceedings of the 10th international conference on World Wide Web. Hong Kong: ACM, 2001: 285-295.
14 GETOOR L, SAHAMI M. Using probabilistic relational models for collaborative filtering [C] // Workshop on Web Usage Analysis and User Profiling. [S.l.]: WEBKDD, 1999: 1-6
15 SHI Y, LARSON M, HANJALIC A Collaborative filtering beyond the user-item matrix: A survey of the state of the art and future challenges[J]. ACM Computing Surveys (CSUR), 2014, 47 (1): 3
16 KINGMA D P, Ba J. Adam: A method for stochastic optimization [J]. arXiv preprint. arXiv: 1412.6980, 2014.
17 ELKAHKY A M, SONG Y, HE X. A multi-view deep learning approach for cross domain user modeling in recommendation systems [C] // Proceedings of the 24th International Conference on World Wide Web. Florence: IW3C2, 2015: 278-288.
18 WANG H, WANG N, YEUNG D Y. Collaborative deep learning for recommender systems [C] // Proceedings of the 21th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. Sydney: ACM, 2015: 1235-1244.
19 MA W J. Deep learning meets recommendation systems [EB/OL]. NYC Data Science Academy. (2017-01-24). [2018-12-17]. https://nycdatascience.com/blog/student-works/deep-learning-meets-recommendation-systems/.
20 XUE H J, DAI X, ZHANG J, et al. Deep matrix factorization models for recommender systems [C] // Proceedings of the 26th International Joint Conference on Artificial Intelligence. Melbourne: AAAI, 2017: 3203-3209.
[1] 张雪峰,陈秀莉,僧德文. 融合用户信任和影响力的top-N推荐算法[J]. 浙江大学学报(工学版), 2020, 54(2): 311-319.
[2] 董立岩,金佳欢,方塬程,王越群,李永丽,孙铭会. 基于非负矩阵分解的Slope One算法[J]. 浙江大学学报(工学版), 2019, 53(7): 1349-1353.
[3] 厉小军,柳虹,施寒潇,朱柳青,张亚辉. 基于深度学习的课程推荐模型[J]. 浙江大学学报(工学版), 2019, 53(11): 2139-2145.
[4] 韩勇, 宁连举, 郑小林, 林炜华, 孙中原. 基于社交信息和物品曝光度的矩阵分解推荐[J]. 浙江大学学报(工学版), 2019, 53(1): 89-98.
[5] 袁友伟, 余佳, 郑宏升, 王娇娇. 基于新颖性排名和多服务质量的云工作流调度算法[J]. 浙江大学学报(工学版), 2017, 51(6): 1190-1196.
[6] 涂鼎, 陈岭, 陈根才, 吴勇, 王敬昌. 基于在线层次化非负矩阵分解的文本流主题检测[J]. 浙江大学学报(工学版), 2016, 50(8): 1618-1626.
[7] 居斌, 钱沄涛, 叶敏超. 基于结构投影非负矩阵分解的协同过滤算法[J]. 浙江大学学报(工学版), 2015, 49(7): 1319-1325.
[8] 苏凯, 马良荔, 孙煜飞, 郭晓明. 面向Web服务QoS预测的非负矩阵分解模型[J]. 浙江大学学报(工学版), 2015, 49(7): 1358-1366.
[9] 岳克强, 孙玲玲, 游彬, 楼立恒. 基于欠定盲分离的并行识别防碰撞算法[J]. 浙江大学学报(工学版), 2014, 48(5): 865-870.
[10] 崔建涛, 厉小润, 赵辽英. 高光谱图像亚像元级地物端元提取方法[J]. J4, 2012, 46(10): 1857-1865.
[11] 厉小润, 伍小明, 赵辽英. 非监督的高光谱混合像元非线性分解方法[J]. J4, 2011, 45(4): 607-613.
[12] 赵武锋 严晓浪. 基于多尺度梯度角和SVM的正面人脸识别方法[J]. J4, 2008, 42(4): 590-592.
[13] 王志梅 杨帆. 基于相似学习者发现的资源推荐系统[J]. J4, 2006, 40(10): 1688-1691.