基于Agent的顾客行为及个性化推荐仿真模型
Agent-based simulation model of customer behavior and personalized recommendation
针对传统个性化推荐研究方法的局限性, 提出一种基于Agent建模与仿真的方法, 通过个体的交互作用所产生的涌现特征来分析移动电子商务环境下的顾客行为及个性化推荐策略的有效性. 以移动商务环境下的餐饮推荐系统为例, 分析了消费活动过程中顾客与服务的交互行为, 以及情境因素对顾客消费的影响, 构建了服务推荐及顾客行为规则, 并在REPAST环境下实现了本Agent仿真模型. 仿真结果表明:该模型可有效分析及预测服务推荐和顾客决策的涌现现象, 并由此推断顾客总体的消费趋势; 同时, 考虑情境因素的推荐模型的有效性比单独基于顾客个性化信息的推荐模型有明显提高.
This paper proposes an agent-based modeling and simulation method to overcome the limitations of traditional personalized recommendation method. Customer behavior and the effectiveness of personalized recommendation strategy under mobile electronic commerce were analyzed according to the emergence generated by the interactions of each agent entity. Taking catering recommendation system under mobile e-commerce as an example, this paper analyzed the interactions of customer and server in consuming process and the impact of context to customer consuming, and the recommendation and customer behavior rules were built, then on this basis the agent simulation model was realized under REPAST simulation environment. The simulation results show that this model can analyze and forecast the emergence of server recommendation and customer decision, and accordingly deduce the general consumer trends. Moreover, the effectiveness of recommendation model considering context is enhanced obviously compared with that of model based on only customer personalization information.
个性化推荐 / Agent建模与仿真 / 情境 / 顾客行为模型 / 有效性评估 {{custom_keyword}} /
personalized recommendation / agent-based modeling and simulation / context / customer behavioral model / effectiveness evaluation {{custom_keyword}} /
[1] 余力, 刘鲁. 电子商务个性化推荐研究[J]. 计算机集成制造系统, 2004, 10(10): 1306-1313.Yu L, Liu L. Research on personalized recommendations in E-business[J]. CIMS, 2004, 10(10): 1306-1313.
[2] 李杰, 徐勇, 王云峰,等. 面向个性化推荐的强关联规则挖掘[J]. 系统工程理论与实践, 2009, 29(8): 144-152.Li J, Xu Y, Wang Y F, et al. Strongest association rules mining for personalized recommendation[J]. Systems Engineering — Theory & Practice, 2009, 29(8): 144-152.
[3] Lee K C, Kwon S. Online shopping recommendation mechanism and its influence on consumer decisions and behaviors: A causal map approach[J]. Expert Systems with Applications, 2008, 35: 1567-1574.
[4] 廖守亿, 戴金海. 复杂适应系统及基于Agent 的建模与仿真方法[J].系统仿真学报, 2004, 16(1): 113-117.Liao S Y, Dai J H. Study on complex adaptive system and agent-based modeling & simulation[J]. Journal of System Simulation, 2004, 16(1): 113-117.
[5] Doniec A, Mandiau R, Piechowiak S, et al. A behavioral multi-agent model for road traffic simulation[J]. Engineering Applications of Artificial Intelligence, 2008, 21: 1443-1454.
[6] 龚晓光, 黎志成. 基于多智能体仿真的新产品市场扩散研究[J]. 系统工程理论与实践, 2003, 23(12): 59-62.Gong X G, Li Z C. Study on multi-agent simulation of new product market diffusion[J]. Systems Engineering — Theory & Practice, 2003, 23(12): 59-62.
[7] 谭满春. 基于Agent与模糊逻辑的车辆换道仿真模型[J]. 系统工程学报, 2007, 22(1): 40-45.Tan M C. Simulation model of vehicle lane-changing based on agent and fuzzy logic[J]. Journal of Systems Engineering, 2007, 22(1): 40-45.
[8] 程贲, 李兴兵, 鲁延京,等. 基于Agent的居民就医选择建模与仿真[J]. 系统工程, 2009, 26(9): 96-101.Cheng B, Li X B, Lu Y J. Agent-based modeling and simulation research into residents healthcare choice[J]. Systems Engineering, 2009, 26(9): 96-101.
[9] Lee W P, Yang T H. Personalizing information appliances: A multi-agent framework for TV programme recommendations[J]. Expert Systems with Applications, 2003, 25: 331-341.
[10] Ahn H J. Evaluating customer aid functions of online stores with agent-based models of customer behavior and evolution strategy[J]. Information Sciences, 2010, 180(9): 1555-1570.
[11] 闫艳, 王锁柱. 基于多Agent 的电子商务个性化推荐系统模型研究[J]. 情报杂志, 2007(5): 59-61.Yan Y, Wang S Z. Research on the model of multi agent-based personalized recommendation system in e-commerce[J]. Journal of Information, 2007(5): 59-61.
[12] 杜静, 叶剑, 史红周,等. 基于贝叶斯网络的多Agent 服务推荐机制研究[J]. 计算机科学, 2010, 37(4): 208-211.Du J, Ye J, Shi H Z, et al. Research on multi-agent service recommendation mechanism based on Bayesian network[J]. Computer Science, 2010, 37(4): 208-211.
[13] 林霜梅, 汪更生, 陈弈秋. 个性化推荐系统中的用户建模及特征选择[J]. 计算机工程, 2007, 33(17): 196-198.Lin S M, Wang G S, Chen Y Q. User modeling and feature selection in personalized recommendation system[J]. Computer Engineering, 2007, 33(17): 196-198.
[14] 李建廷. 基于简化ODP的用户兴趣模型[J]. 计算机工程与科学, 2010, 32(5): 121-123.Li J T. A user interest model based on the basic structure of ODP[J]. Computer Engineering & Science, 2010, 32(5): 121-123.
[15] 李晓昀, 阳小华, 余颖. 基于隐性反馈分析的个性化推荐研究[J]. 计算机工程与设计, 2009, 30(16): 3794-3796.Li X Y, Yang X H, Yu Y. Research on individualized recommendation based on implicit feedback analyses[J]. Computer Engineering and Design, 2009, 30(16): 3794-3796.
[16] Kwon K, Cho J H, Park Y. Influences of customer preference development on the effectiveness of recommendation strategies[J]. Electronic Commerce Research and Applications, 2009, 8: 263-275.
[17] Schoefegger K, Seitlinger P, Ley T. Towards a user model for personalized recommendations in work-integrated learning: A report on an experimental study with a collaborative tagging system[J]. Procedia Computer Science, 2010, 1(2): 2829-2838.
[18] Mobasher B, Dai H, Luo T, et al. Improving the effectiveness of collaborative filtering on anonymous Web usage data[C]// The IJCAI 2001 Workshop on Intelligent Techniques for Web Personalization, Seattle, USA, 2001: 53-60.
[19] 王有为, 许博, 卫学启, 等. 基于用户访问序列聚类的网站导航系统[J]. 系统工程理论与实践, 2010, 30(7): 1305-1311.Wang Y W, Xu B, Wei X Q, et al. Website navigation systems based on user accessing sequences clustering[J]. Systems Engineering — Theory & Practice, 2010, 30(7): 1305-1311.
[20] 冀俊忠, 沙志强, 刘椿年. 一种基于贝叶斯网客户购物模型的商品推荐方法[J].计算机应用研究, 2005(4): 65-68.Ji J Z, Sha Z Q, Liu C N. A method of commodity recommendation based on customer shopping model of Bayesian network[J]. Application Research of Computers, 2005(4): 65-68.
国家自然科学基金重大项目(70890080, 70890083)
/
〈 | 〉 |