基于模拟评分的服装推荐改进算法

doi:10.13475/j.fzxb.20210204107

摘要/Abstract

摘要：

针对传统服装推荐算法中缺乏对消费者与服装特性的关注,以及预测结果缺乏针对性和有效性的问题,利用服装编码、时间间隔和欧氏距离等参数构建了消费者购物兴趣衰减模型,提出基于模拟评分的服装推荐改进算法。对比了模拟评分算法与基于奇异值分解的改进算法的预测值和真实值之间的平均绝对误差。结果表明:模拟评分算法预测评分的平均绝对误差为0.808,相对于基于奇异值分解的改进算法,误差降低了0.024,其中25%的个案的误差大于1,排除这部分个案后的平均绝对误差为0.632;通过对消费者进行回访分析发现,90%消费者的推荐准确率大于96%,只有10%的消费者的推荐准确率为60%~64%;导致误差较大的原因是这部分消费者的喜好发生变化,或是长期没有购买服装。

Abstract:

The traditional clothing recommendation algorithms do not pay enough attention to consumers and clothing characteristics, hence the prediction results are short in pertinence and effectiveness. To improve on these, a model of consumers' interest attenuation in shopping was constructed by using clothing coding, time interval and Euclidean distance, and an improved clothing recommendation algorithm based on simulation scoring was proposed. By comparing the average absolute error between the true values and the predicted values of the simulation scoring algorithm and the improved algorithm based on singular value decomposition, it is found that the average absolute error of the simulation scoring algorithm is 0.808, which is 0.024 lower than that of the improved algorithm based on singular value decomposition. The error of 25% of all cases is bigger than 1, and the average error after excluding this part of cases is 0.632. Through such case analysis, it is found that the average absolute accuracy of 90% recommendation is greater than 96%, and the accuracy of 10% recommendation is between 60% and 64%. The reason for big error is either because of the preference changes of the targeted consumer groups, or the targeted consumer group have not purchased clothes for a long time.

Key words: clothing recommendation algorithm, sparce data, simulation scoring, convolution neural network, Euclidean distance

中图分类号:

TS941.73

江学为, 田润雨, 卢方骁, 张艺. 基于模拟评分的服装推荐改进算法[J]. 纺织学报, 2021, 42(12): 138-144.

JIANG Xuewei, TIAN Runyu, LU Fangxiao, ZHANG Yi. Improved clothing recommendation algorithm based on simulation scoring[J]. Journal of Textile Research, 2021, 42(12): 138-144.

图/表 9

图1

表1

图2

图3

图4

表2

图5

表3

图6

参考文献 19

[1]	黄立威, 江碧涛, 吕守业, 等. 基于深度学习的推荐系统研究综述[J]. 计算机学报, 2018, 41:191-219.
	HUANG Liwei, JIANG Bitao, LÜ Shouye, et al. Survey on deep learning based recommender systems[J]. Chinese Journal of Computers, 2018, 41:191-219.
[2]	ADOMAVICIUS G, TUZHILIN A. Toward the next generation of recommender systerms: a survey of the state of the art and possible extensions[J]. IEEE Transactions on Knowledge and Data Engineering, 2005, 17(6):734-749. doi: 10.1109/TKDE.2005.99
[3]	张卓, 丛洪莲, 蒋高明, 等. 基于交互式遗传算法的Polo衫快速款式推荐系统[J]. 纺织学报, 2021, 42(1):138-144.
	ZHANG Zhuo, CONG Honglian, JIANG Gaoming, et al. Polo shirt rapid style recommendation system based on interactive genetic algorithm[J]. Journal of Textile Research, 2021, 42(1):138-144.
[4]	司梦楚. 基于混合召回模型的服装智能推荐系统[D]. 青岛: 青岛大学, 2020:1-2.
	SI Mengchu. Intelligent clothing recommendation system based on hybrid recall model[D]. Qingdao: Qingdao University, 2020:1-2.
[5]	陈颖, 侯惠敏. 基于项目属性偏好挖掘的协同过滤推荐算法[J]. 计算机应用, 2017(S1):269-272.
	CHEN Ying, HOU Huimin. Collaborative filtering recommendation algorithm based on item attribute preference mining[J]. Journal of Computer Applications, 2017(S1):269-272.
[6]	屠青青. 基于关键点服装款式识别的智能时尚推荐系统研究[D]. 成都:电子科技大学, 2014: 27-32.
	TU Qingqing. Research of key point based style recognition and intelligent fashion clothing recommendation system[D]. Chengdu: University of Electronic Science and Technology of China, 2014: 27-32.
[7]	翁小兰, 王志坚. 协同过滤推荐算法研究进展[J]. 计算机工程与应用, 2018, 54(1):25-31.
	WENG Xiaolan, WANG Zhijian. Progress in collaborative filtering recommendation algorithm[J]. Computer Engineering and Applications, 2018, 54(1):25-31.
[8]	单毓馥, 李丙洋. 电子商务推荐系统中服装推荐问题研究[J]. 毛纺科技, 2016, 44(5):66-69.
	SHAN Yufu, LI Bingyang. Researeh on apparel reco mendation in e-commerce recommender systems[J]. Wool Textile Journal, 2016, 44(5):66-69.
[9]	尹定乾, 杨佳乐, 金英花. 基于局部SVD++的服装推荐算法研究[J]. 价值工程, 2018, 37(10):173-176.
	YIN Dingqian, YANG Jiale, JIN Yinghua. Research on clothing recommendation algorithm based on local SVD++[J]. Value Engineering, 2018, 37(10):173-176.
[10]	范福军, 陈畅足, 陈方明. 中小服装企业的电子商务转型模式[J]. 纺织学报, 2014, 35(3):145-150.
	FAN Fujun, CHEN Changzu, CHEN Fangming. Electronic commerce transformation modes for small and medium-sized garment enterprises[J]. Journal of Textile Research, 2014, 35(3):145-150.
[11]	张磊, 陈红华. 全渠道零售商营销协同对消费者购买意愿的影响:基于多群组结构方程模型分析[J]. 中国流通经济, 2019, 33(8):108-117.
	ZHANG Lei, CHEN Honghua. Research on the influence of omni-channel retailers' marketing collaboration on consumers' purchase intention: based on multi-group structural equation model[J]. China Business and Market, 2019, 33(8):108-117.
[12]	邬适融, 陈洁, 曾艺生, 等. 消费者持续满意度研究:基于快乐适应视角[J]. 南开管理评论, 2011, 14(1):130-137, 156.
	WU Shirong, CHEN Jie, ZENG Yisheng, et al. A research on consumers' sustainable satisfaction: an investigation from hedonic adaption perspective[J]. Nankai Business Review, 2011, 14(1):130-137, 156.
[13]	王夏阳, 陈思霓, 邬金涛. 网络预售下消费者购买行为的影响因素分析:基于淘宝2018春夏女装的实证研究[J]. 南开管理评论, 2020, 23(5):4-15,40.
	WANG Xiayang, CHEN Sini, WU Jintao. On the factors influencing online consumers-purchasing behavior under pre-order strategy: an empirical study based on womens 2018 spring-summer apparels of tmall[J]. Nankai Business Review, 2020, 23(5):4-15,40.
[14]	熊万强, 王蓓莉, 孙晓光. 基于生物记忆原理的智能词汇记忆模型[J]. 计算机工程, 2015, 41(6):254-257.
	XIONG Wanqiang, WANG Beili, SUN Xiaoguang. Intelligent vocabulary memory model based on biological memory principle[J]. Computer Engineering, 2015, 41(6):254-257.
[15]	薛树强, 杨元喜. 广义反距离加权空间推估法[J]. 武汉大学学报(信息科学版), 2013(12):52-56.
	XUE Shuqiang, YANG Yuanxi. Generalized inverse distance weighting method for spatial interpolation[J]. Geomatics and Information Science of Wuhan University, 2013(12):52-56.
[16]	杨笑锋. 多维数据融合的电影推荐系统研究与实现[D]. 昆明:昆明理工大学, 2017:25-27.
	YANG Xiaofeng. Research and implementation of movie recommendation system based on multidimensional data fusion[D]. Kunming: Kunming University of Science and Technology, 2017:25-27.
[17]	冯兴杰, 张志伟, 史金钏. 基于卷积神经网络和注意力模型的文本情感分析[J]. 计算机应用研究, 2018(5):1434-1436.
	FENG Xingjie, ZHANG Zhiwei, SHI Jinchuan. Text sentiment analysis based on convolutional neural networks and attention model[J]. Application Research of Computers, 2018(5):1434-1436.
[18]	LIKERT R. A technique for the measurement of atti-tudes[J]. Archieves of Psychology, 1932, 22:1-55.
[19]	梁昌勇, 冷亚军, 王勇胜, 等. 电子商务推荐系统中群体用户推荐问题研究[J]. 中国管理科学, 2013, 21(3):153-158.
	LIANG Changyong, LENG Yajun, WANG Yongsheng, et al. Research on group recommendation in e-commerce recommender systems[J]. Chinese Journal of Management Science, 2013, 21(3):153-158.

Metrics

Viewed

Full text

Abstract

Cited

Shared

Discussed

服装编号	标签	一级编码	二级编码
1	韩版、原宿、纯棉、宽松、 T恤、短袖、露肩、上衣	(1,1,1)	(1,1,1,1,1,0, 0,0,0,0,0,0)
2	韩版、简约、圆领、套头、修身、露肚脐、短袖、T恤	(1,0,1)	(1,0,0,0,0,1, 1,1,1,1,0,0)
3	宽松、T恤、原宿、韩版、百搭、上衣、慵懒风	(1,1,0)	(1,1,1,0,0,0, 0,0,0,0,1,1)