基于用户兴趣行为模型的个性化广告推荐研究

随着移动互联网和网络终端的快速发展,产品的营销方式发生了重大变化,在互联网上投放广告已成为商家的重要宣传和销售渠道。然而,在线广告能否进行准确推荐是困扰产品厂家和广告代理商的一个主要问题。文章通过分析在线广告的非结构化特征和搜索用户行为数据,提出一种基于用户兴趣行为模型的个性化广告推荐方法,该方法可以通过主题模型提取用户的兴趣偏好,并基于最近邻算法和用户行为生成广告推荐列表。实验结果表明,基于最近邻算法和用户行为的个性化广告推荐方法可以推荐个性化广告,并且比基于内容的推荐方法具有更好的性能。     

顾客偏好的动态挖掘算法

基于顾客偏好随时间变化的特性，采用聚类、关联规则等技术，对顾客偏好进行动态挖掘．通过追踪顾客购买序列，最终产生Top N产品推荐，旨在提高推荐系统的推荐质量．然后选取协同过滤算法作对照，并采用MovieLens站点提供的测试数据集．通过对召回率和精度两项指标的分析，表明该动态挖掘算法具有较高的推荐准确度和全面性．     

基于Web Mining的推荐系统

推荐系统(Recommender System)被电子商务站点用来向顾客提供信息以帮助顾客选择产品,其基本思想是以统计结果或者顾客以前的行为记录为依据,推测顾客未来可能的行为并给出相应的推荐。本文对基于传统技术和Web mining技术的推荐系统进行了简要综述,同时描述了基于Web mining技术的推荐系统的工作流程,重点分析了应用于推荐系统的各种具体Web mining技术及其算法比较。     

基于多目标优化策略的在线学习资源推荐方法

目前在线学习资源推荐较多采用单目标转化方法,推荐过程中对学习者偏好考虑相对不足,影响学习资源推荐精度.针对上述问题,文中提出基于多目标优化策略的在线学习资源推荐模型(MOSRAM),在学习者规划时间内,以同时获得学习者对学习资源类型偏好度最大和难度水平适应度最佳为优化目标,设计具有向邻居均值学习能力和探索新区域能力的多目标粒子群优化算法(NEMOPSO),提出以MOSRAM为核心的在线学习资源推荐方法(NEMOPSO-RA).不同问题规模下融合经典多目标优化算法的推荐方法对比实验表明,NEMOPSO-RA可以有效提高在线学习资源的推荐精度和推荐性能.     

基于动态和静态偏好的兴趣点推荐算法

针对大多数现有主流兴趣点(POI)推荐算法忽略了融合用户复杂动态偏好和一般静态偏好建模的复杂性问题,提出一个融合复杂动态用户偏好和一般静态用户偏好的POI推荐算法CLSR.首先,在复杂动态偏好建模过程中,基于用户的签到行为及其中的跳过行为设计一个混合神经网络,实现用户的复杂动态兴趣的建模;其次,在一般静态偏好建模过程中...     

基于用户重购行为的产品推荐方法

重复购买是消费者日常消费决策中的常见现象,考虑用户重购行为对于提升产品个性化推荐准确性至关重要.然而针对用户重购行为建模和预测的研究工作相对较少,还有很多问题有待解决.已有推荐技术主要通过深度挖掘产品、用户或时间某一层面信息来进行重购产品推荐,忽略了对多层次信息融合建模方法的研究,同时也忽略了重购推荐结果的可解释性需求.因此,融合多层次用户偏好信息,构建了具有双层注意力机制的可解释用户重复消费推荐方法.该方法融合注意力机制和指针生成网络,多层次提取并学习用户重购偏好,同时基于信息处理理论构建S型用户重购动态偏好函数,融合产品流行度信息进行重购产品和新颖产品的混合推荐,提高了模型可解释性和准确性.真实数据集上的实验结果表明,所提方法在多个性能指标上都优于对比方法,且学习出的参数具备较好的可解释性.此外,通过回归分析验证了S型重购动态偏好函数的可信性,进一步增强了理论的可解释性.     

基于用户行为数据的电网企业营销推荐系统设计

由于目前方法未能分析和挖掘电网用户行为,使用户的商品属性偏好与预计营销偏好存在差异,导致电网企业营销推荐结果不理想,为此提出基于用户行为数据的电网企业营销推荐系统。通过系统硬件和软件相互协作设计,从用户历史行为出发,优先分析处理用户的历史交互行为,对用户的行为喜好进行分类,挖掘用户的商品属性偏好,实现用户近期需求预测以及意向商品推荐。实验结果证明,所设计系统能够有效提升推荐速率和用户满意度,获取效果较好的推荐结果。     

基于用户偏好特征挖掘的个性化推荐算法

为了提升社交网络个性化推荐能力,结合用户行为分布进行个性化推荐设计,文中提出基于用户行为特征挖掘的个性化推荐算法,构建社交网络的用户行为信息特征挖掘模型,采用显著数据分块检测方法对社交网络用户特征的行为信息进行融合处理,提取反映用户偏好的语义信息特征量。从情感、关键词和结构等方面根据用户行为特征组,结合模糊信息感知方法进行社交网络个性化推荐过程中的信息融合处理,在关联规则约束控制下,构建社交网络用户偏好特征的混合推荐模型,实现用户偏好特征挖掘,根据语义分布和用户的行为偏好实现社交网络的个性化信息推荐。仿真结果表明,采用所提方法进行社交网络个性化推荐的特征分辨能力较好,对用户行为特征的准确识别能力较强,提高了社交网络推荐输出的准确性。     

基于偏好的客户模糊聚类方法

在电子商务环境下,如何按照顾客的购买兴趣进行聚类分析并为其提供个性化服务,是电子商务应用中研究的热点课题之一时.顾客的浏览行为及兴趣进行了研究,提出了利用偏好度的方法来度量顾客的兴趣度,在此基础上给出了基于偏好的客户群聚类算法.在该算法中,依据Web日志数据计算顾客偏好度,建立偏好度矩阵,再利用模糊聚类方法对顾客进行聚类.并用实例说明了具体的聚类过程.     

基于用户行为的个性化电商信息推送系统设计

为提高推荐产品与用户需求产品的适配度,基于用户行为分析设计了一种针对电子商务的个性化信息推荐系统。首先,使用网络爬虫技术检索电子商务平台的运行终端,获取电商用户行为信息;其次,构建电商用户行为信息表,分析获取的用户行为数据,通过用户对产品需求来计算用户的偏好度;最后,引进关联规则,挖掘符合用户喜好的产品,实现个性化信息主动推送服务。实验证明,该系统推荐的商品与用户需求产品两者适配度在90%以上,且系统推送后,显著提升了用户在电商平台的点击次数与浏览时间。     

Eliciting Customer Preferences for Products From Navigation Behavior on the Web: A Multicriteria Decision Approach With Implicit Feedback

The goal of raising customer loyalty in electronic commerce requires an emphasis on one-to-one marketing and personalized services. To this end, it is essential to understand individual customer preferences for products. In this paper, we present a method for identifying customer preferences and recommending the most appropriate product. The identification and recommendation of such products are all based on the use of customer's real-time web usage behavior, including activities such as viewing, basket placement, and purchasing of products. Therefore, in this approach, we do not force a customer to explicitly express his or her preference information for particular products but rather capture his or her preferences from data that result from such activities. Information on the web usage behavior for the products determines the ordinal relationships among the products, which express that certain product is preferred to other products across the multiple aspects. The ordinal relationships among the products and the multiple aspects of products lead to the consideration of a multiple-criteria decision-making approach. Thus, the problem eventually results in the identification of weights attached to the multiple criteria in the multidimensional preference space constructed by the ordinal relationships among the products. The derived weights are then used for the prioritization of products that are not included in the navigation behavior due to factors such as time pressure, cognitive burden, and the like.     

产品外形设计中客户感性认知模型及应用

为了更好地利用客户的感性认知支持产品外形设计活动,提出一种产品外形设计中客户感性认知与产品外形特征关联模型.在分析产品外形设计中所涉及的客户感性认知特点的基础上,建立产品外形特征要素与客户感性认知要素的关联模式;以认知行为为标准,利用特征匹配实现了客户感性认知的识别与相似性分析;提出了基于模糊认知图的客户感性认知与产品外形特征关联模型,利用蚁群聚类算法确定模糊认知图的结构及邻接矩阵,从而获取客户感性认知以指导产品的外形设计.最后通过实例验证了该模型的有效性和实用性.     

An agent-based recommender system for developing customized families of products

Electronic markets and web-based content have improved traditional product development processes by increasing the participation of customers and applying various recommender systems to satisfy individual customer needs. Agent-based systems based on agents’ roles and tasks can provide appropriate tools to solve product design problems by recommending design knowledge and information. This paper introduces an agent-based recommender system to support designing families of products based on customers’ preferences in dynamic electronic market environments. In the proposed system, a market-based learning mechanism is applied to determine the customers’ preferences for recommending appropriate products to customers of the product family. We demonstrate the implementation of the proposed recommender system using a multi-agent framework. Through simulated experiments, we illustrate that the proposed recommender system can help determine the preference values of products for customized recommendation and market segment design in various electronic market environments.     

网上零售业多产品配送服务定价研究

随着越来越多的网上零售商开始实施有条件的免运费策略, 如何确定免运费的条件和运费成为电商企业面临的重要问题。该问题抽象成为一个两阶段的博弈模型：首先消费者根据效用最大化的原则确定购买决策, 然后零售商在考虑消费者购买决策的基础上依据利润最大化原则设定物流定价策略。通过算法设计和算例分析, 得到免运费阈值设定在产品价格组合边界时, 零售商利润会发生跳跃。     

Predicting user behavior in electronic markets based on personality-mining in large online social networks

Determining a user’s preferences is an important condition for effectively operating automatic recommendation systems. Since personality theory claims that a user’s personality substantially influences preference, I propose a personality-based product recommender (PBPR) framework to analyze social media data in order to predict a user’s personality and to subsequently derive its personality-based product preferences. The PBRS framework will be evaluated as an IT-artefact with a unique online social network XING dataset and a unique coffeemaker preference dataset. My evaluation results show (a) the possibility of predicting a user’s personality from social media data, as I reached a predictive gain between 23.2 and 41.8 percent and (b) the possibility of recommending products based on a user’s personality, as I reached a predictive gain of 45.1 percent.     

Applying case-based reasoning for product configuration in mass customization environments

Product variation and customization is a trend in current market-oriented manufacturing environment. Companies produce products in order to satisfy customer's needs. In the customization environment, the R&D sector in an enterprise should be able to offer differentiation in product selection after they take the order. Such product differentiation should meet the requirement of cost and manufacturing procedure. In the light of this, how to generate an accurate bill of material (BOM) that meets the customer's needs and gets ready for the production is an important issue in the intensely competitive market.

The purpose of this study is to reduce effectively the time and cost of design under the premise to manufacture an accurate new product. In this study, the Case-Based Reasoning (CBR) algorithm was used to construct the new BOM. Retrieving previous cases that resemble the current problem can save a lot of time in figuring out the problem and offer a correct direction for designers. When solving a new problem, CBR technique can quickly help generate a right BOM that fits the present situation.     

Intelligent agent-based systems for personalized recommendations in Internet commerce

The prosperity of electronic commerce has changed the traditional trading behaviors and more and more people are willing to conduct Internet shopping. However, the exponentially increasing information provided by the Internet enterprises causes the problem of overloaded information, and this inevitably reduces the customer's satisfaction and loyalty. One way to overcome such a problem is to build personalized recommender systems to retrieve product information that really interests the customers. For products that people may purchase relatively often, such as books and CDs, recommender systems can be built to reason about a customer's personal preferences from his purchasing history and then provide the most appropriate information services to meet his needs. On the other hand, for those commodities a general customer does not buy frequently, for example computers and home theater systems, more appropriate are the kinds of recommender systems able to retrieve optimal products based on the customer's current preferences obtained from the iterative system–customer interactions. This paper presents the above two kinds of recommender systems we have developed for supporting Internet commerce. Experimental results show the promise of our systems.     

面向大众消费者的产品感性定制模型及其应用

为了使产品定制模型更加适合缺少相关领域专业知识的大众消费者,建立了基于感性工学的产品感性定制模型.将顾客对产品的感性意象作为定制需求,对其进行分类并量化,利用层次分析法评价待选的产品工程配置实例,获得最符合顾客感性意象需求的产品工程配置.最后用自行车定制系统实例说明了该模型的应用.     

电子市场中组合客户联盟模型及遗传算法设计

在电子市场中,客户联盟可以为买卖双方赢得更多利润。该文提出了一个组合顾客联盟模型,可同时描述顾客偏好和商品数量。并针对此复杂的组合优化问题,给出了用遗传算法求解的框架。