Item-level RFID for enhancement of customer shopping experience in apparel retail

In the customer-oriented apparel retail industry, providing satisfactory shopping experience for customers is a vital differentiator. However, traditional stores generally cannot fully satisfy customer needs because of difficulties in locating target products, out-of-stocks, a lack of professional assistance for product selection, and long waiting for payments. Therefore, this paper proposes an item-level RFID-enabled retail store management system for relatively high-end apparel products to provide customers with more leisure, interaction for product information, and automatic apparel collocation to promote sales during shopping. In this system, RFID hardware devices are installed to capture customer shopping behaviour and preferences, which would be especially useful for business decision-making and proactive individual marketing to enhance retail business. Intelligent fuzzy screening algorithms are then developed to promote apparel collocation based on the customer preferences, the design features of products, and the sales history accumulated in the database. It is expected that the proposed system, when fully implemented, can help promote retail business by enriching customers with intelligent and personalized services, and thus enhance the overall shopping experience.     

Applying virtual reality for trust-building e-commerce environments

The application of virtual reality in e-commerce has enormous potential for transforming online shopping into a real-world equivalent. However, the growing research interest focuses on virtual reality technology adoption for the development of e-commerce environments without addressing social and behavioral facets of online shopping such as trust. At the same time, trust is a critical success factor for e-commerce and remains an open issue as to how it can be accomplished within an online store. This paper shows that the use of virtual reality for online shopping environments offers an advanced customer experience compared to conventional web stores and enables the formation of customer trust. The paper presents a prototype virtual shopping mall environment, designed on principles derived by an empirically tested model for building trust in e-commerce. The environment is evaluated with an empirical study providing evidence and explaining that a virtual reality shopping environment would be preferred by customers over a conventional web store and would facilitate the assessment of the e-vendor’s trustworthiness.     

Discovering patterns of online purchasing behaviour and a new‐product‐launch strategy

Spurred by rapid development of computers and Internet technology, online shopping is gradually overtaking in‐store shopping, because of advantages such as convenience, more choice of products or services etc. Online stores must devote a great deal of time and resources to locating and attracting new customers. Growing a customer base requires first understanding customers and then providing the products or services they need, thus encouraging customers to purchase more. This paper develops a system to analyse customers’ purchasing behaviour and track shifts in their interests. Customers’ purchasing behaviour is measured using proposed standard product loyalty status and standard brand loyalty status. Using these metrics, together with the preference map established for each customer, a marketing specialist can easily locate potential customers to target when a company launches a new product. The new‐product‐launch strategy proposed in this paper can be used to create a list of potential customers for a product being launched under a variety of conditions. A prototype system has been built to test the feasibility of the proposed new‐product‐launch strategy. The result shows almost 40% of potential customers respond to the recommendation positively.     

基于网格热度值的船舶规律路径提取算法

随着无线传感器、卫星、GPS(global positioning system)等移动目标定位技术的发展,产生的移动数据(诸如人类足迹、车辆行驶轨迹和船舶轨迹等)的规模越来越大.而移动目标检测设备只会存储一系列离散点的信息,所以基于离散点来追踪和恢复其完整的轨迹是更加全面掌握移动目标运动规律的必要前提.数据挖掘方法能从移动目标的历史位置信息中挖掘出“规律”路径,其中基于网格的聚类分析方法不仅能有效表达这些轨迹点,还能分析出这些轨迹点之间的关系,是提取规律路径的有效方法.为此,提出了基于网格“热度值”的距离和密度相结合的热度因子相似性度量方法,进而给出了移动目标规律路径提取算法.最后,使用船舶自动识别系统(automatic identification system, AIS)生成的船舶实际动态数据进行测试,来验证该算法的精度和性能.算法分析和实验结果表明:基于网格热度值的规律路径提取算法能有效地发现不同形状的轨迹序列.     

基于复杂属性相似度的聚类算法及其应用研究

针对电信客户的有效细分问题,利用属性相似度度量思想,提出了一种面向复杂属性的聚类算法。该算法用复杂属性分布相似度函数衡量对象的相似性,然后根据相似性建立图模型,最后对图进行分割进行聚类。相比于传统基于选维和降维的聚类分析算法,提出的算法能有效处理高维数据和复杂属性。同时,算法在参数调节时,不需遍历原始数据,也减少了人工干预。利用真实电信客户数据进行的模拟实验也表明,提出的算法具有良好性能,可以有效解决电信客户细分问题。     

A fuzzy-based customer clustering approach with hierarchical structure for logistics network optimization

Customer clustering is an essential step to reduce the complexity of large-scale logistics network optimization. By properly grouping those customers with similar characteristics, logistics operators are able to reduce operational costs and improve customer satisfaction levels. However, due to the heterogeneity and high-dimension of customers’ characteristics, the customer clustering problem has not been widely studied. This paper presents a fuzzy-based customer clustering algorithm with a hierarchical analysis structure to address this issue. Customers’ characteristics are represented using linguistic variables under major and minor criteria, and then, fuzzy integration method is used to map the sub-criteria into the higher hierarchical criteria based on the trapezoidal fuzzy numbers. A fuzzy clustering algorithm based on Axiomatic Fuzzy Set is developed to group the customers into multiple clusters. The clustering validity index is designed to evaluate the effectiveness of the proposed algorithm and find the optimal clustering solution. Results from a case study in Anshun, China reveal that the proposed approach outperforms the other three prevailing algorithms to resolve the customer clustering problem. The proposed approach also demonstrates its capability of capturing the similarity and distinguishing the difference among customers. The tentative clustered regions, determined by five decision makers in Anshun City, are used to evaluate the effectiveness of the proposed approach. The validation results indicate that the clustered results from the proposed method match the actual clustered regions from the real world well. The proposed algorithm can be readily implemented in practice to help the logistics operators reduce operational costs and improve customer satisfaction levels. In addition, the proposed algorithm is potential to apply in other research domains.     

参考节点嵌入最短距离估算在图聚类中的应用

为解决社会关系网络图中节点没有坐标值、不能采用传统的欧几里得距离和曼哈坦距离进行聚类的问题,提出采用最短路径算法,来衡量点与点之间的相异度.针对最短路径算法具有时间复杂度大的缺点,引入基于参考节点嵌入的最短距离估算思想来估算两点之间的近似距离.在此基础上,针对DBLP数据集构成的社会关系网络图进行聚类,使用基于划分的k-medoids算法,分别采用以上两种距离算法,比较其优劣.实验证明改进后的算法和最短路径算法中的Dijkstra 算法相比,距离误差率小,时间复杂度大大降低,在提高效率的同时,取得了同样好的聚类效果.     

Which is more important in Internet shopping,perceived price or trust?

Price and trust are considered to be two important factors that influence customer purchasing decisions in Internet shopping. This paper examines the relative influence they have on online purchasing decisions for both potential and repeat customers. The knowledge of their relative impacts and changes in their relative roles over customer transaction experience is useful in developing customized sales strategies to target different groups of customers. The results of this study revealed that perceived trust exerted a stronger effect than perceived price on purchase intentions for both potential and repeat customers of an online store. The results also revealed that perceived price exerted a stronger influence on purchase decisions of repeat customers as compared to that of potential customers. Perceived trust exerted a stronger influence on purchase decisions of potential customers as compared to that of repeat customers.     

Evaluating customer aid functions of online stores with agent-based models of customer behavior and evolution strategy

With competitive pressure growing in online markets, many Internet stores provide various customer aid functions such as personalized pages to help customers shop more effectively and efficiently. Evaluating such customer aid functions is usually costly because it requires full or partly-working systems and many human testers. In order to address this problem, this research presents a novel approach to evaluating customer aid functions with agent-based models of customer behavior and evolution strategies. Agent-based modeling is used to imitate users’ rational behavior at Internet stores with regard to browsing and collecting product information. It is assumed that users evolve their browsing skill and strategy over time, to maximize the efficiency and effectiveness of their shopping, and hence, evolution strategy, an optimization method, is combined with the agent-based model to find the rational behavior of each user. The rational behavior is then used to simulate the virtual shopping of users and to evaluate the performances of target customer aid functions. Several experiments were performed to illustrate the use of the approach, where the personalized recommendation page of a virtual online DVD rental store is evaluated in comparison with more general functions such as listing most popular products or sorting categories. The results show that a personalized page might not always be the best customer aid function for all users compared to the simpler ones.     

String analysis technique for shopping path in a supermarket

The sensor network technology developed in recent years has made it possible to accurately track the in-store behavior of customers which was previously indeterminable. The information on the in-store behavior of customers obtained by using this technology, namely information on their shopping path, provides us with useful information concerning the customer’s purchasing behavior. The purpose of this research is to apply character string analysis techniques to shopping path data so as to analyze customers’ in-store behavior, and thereby clarify technical problems with them (the character string analysis techniques) as well as their usability. In this paper we generated character strings on visit patterns to store sections by focusing exclusively on customers stopping by these sections in order to elucidate the visiting patterns of customers who made a large quantity of purchases. In this paper, we were able to discover useful information by using the character string analysis technique EBONSAI, thereby illustrating the usability and usefulness of character string analysis techniques in shopping path analysis.     

Wheel hub customization with an interactive artificial immune algorithm

With the transformation from traditional manufacturing to intelligent manufacturing, customer-oriented personalized customization has gradually become the main mode of production. Interactive algorithms determine the pros and cons of the solution via customers which can make customers better participants in the customization process. However, if the population size is expanded and the number of evolutionary iterations is too high, frequent interactions are likely to cause customer fatigue. This paper proposes an adaptive interactive artificial immune algorithm based on improved hierarchical clustering. This algorithm uses the improved hierarchical clustering algorithm to optimize generation of the initial antibodies and applies the affinity calculation method based on customer intention, adaptive crossover and mutation operators, and a multisolution reservation method based on hybrid selection strategy to the artificial immune algorithm. Via empirical research on the customized operational data of wheel hubs, the proposed method effectively solves the problem of customer fatigue, significantly improves the convergence speed of the algorithm and reduces the time cost.

     

基于遗传算法的超市最短导购路径推荐

大型超市里商品数目的繁多、空间布局的复杂往往容易让消费者迷失在室内,花费大量时间进行商品搜寻。提出基于遗传算法的超市导购路径推荐方法,通过对超市的空间布局结构离散化建模,生成分别用节点和无向边表示商品区域和区域之间可行走路线的平面图;结合消费者的采购清单,根据商品所在的货架位置将商品与具体的区域做出匹配,用遗传算法优化生成一条联结超市入口、要采购的商品区域以及结账柜台的最短路线。Matlab的仿真结果显示,该方法简单、高效,能够快速为消费者推荐出最短路线,供其购物参考。     

聚类分析在电信家庭客户细分中的应用

电信行业的客户细分多数集中在政企客户,很少涉及到家庭客户,而家庭市场一直是电信运营商的大本营。该文采用数据挖掘中的K-means聚类算法,建立客户细分模型,对电信家庭客户进行细分,为进一步挖掘家庭信息服务需求,实现精细化营销奠定基础。     

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.     

Group RFM analysis as a novel framework to discover better customer consumption behavior

The RFM model provides an effective measure for customers’ consumption behavior analysis, where three variables, namely, consumption interval, frequency, and money amount are used to quantify a customer’s loyalty and contribution. Based on the RFM value, customers can be clustered into different groups and the group information is very useful in market decision making. However, most previous works completely left out important characteristics of purchased products, such as their prices and lifetimes, and apply the RFM measure on all of a customer’s purchased products. This renders the calculation of the RFM value unreasonable or insignificant for customer analysis. In this paper, we propose a new framework called GRFM (for group RFM) analysis to alleviate the problem. The new measure method takes into account the characteristics of the purchased items so that the calculated the RFM value for the customers are strongly related to their purchased items and can correctly reflect their actual consumption behavior. Moreover, GRFM employs a constrained clustering method PICC (for Purchased Items-Constrained Clustering) that could base on a cleverly designed purchase pattern table to adjust original purchase records to satisfy various clustering constraints as well as to decrease re-clustering time. The GRFM allows a customer to belong to different clusters, and thus to be associated with different loyalties and contributions with respect to different characteristics of purchased items. Finally, the clustering result of PICC contains extra information about the distribution status inside each cluster that could help the manager to decide when is most proper to launch a specific sales promotion campaign. Our experiments have confirmed the above observations and suggest that GRFM can play an important role in building a personalized purchasing management system and an inventory management system.     

Formulation of customers’ shopping path in shelf space planning: A simulation-optimization approach

Numerous studies confirm that customers’ shopping behavior can highly be managed by many in-store factors such that retail managers try to systematically consider them in order to achieve a well-established solution for shelf-space allocation problem (SSAP). To assist them, we develop an approach based on two artificial intelligence techniques to facilitate well-designed shelf space management. We propose an iterative simulation-optimization approach that integrates customers’ shopping path in the potential demand and introduces it by simulation in the optimization. A profit-based integer programming is also presented that the related computer program, being able to solve small-sized instances, applies important factors including shelf level utility, attraction of store’ zones, allocated shelf space, number of product facings, and demand substitution effects. The problem is inherently a complex and large-sized problem; therefore, we develop two algorithms: GA and hybrid GA with imperialist competitive algorithm. The experimental results prove good performance of hybrid algorithm in terms of both the solution quality and computation time. By embedding this flexible and powerful framework in an expert tool, retail managers are capable of making effective decisions.     

Dynamic argument embedding: preserving state on the World Wide Web

At the IBM T.J. Watson Research Center we implemented a way of preserving state during HTTP sessions by modifying hypertext links to encode state information. We call the method dynamic argument embedding, and it was developed in response to problems we encountered implementing the Coyote Virtual Store, a transaction-processing system prototype. Virtual store applications, such as IBM's NetCommerce and Netscape's Merchant System, typically need to maintain information such as the contents of shopping baskets while customers are shopping. We wanted our application to be flexible enough to maintain such state information without restricting the sorts of HTML pages a customer might view. We also wanted a system that did not require extensions to the hypertext transfer protocol (HTTP) and so could be implemented on any standard Web server and client browser. Finally, we wanted to permit customers to access several accounts at once by using the browser's cache to concurrently store pages corresponding to multiple invocations of the virtual store application     

Understanding the product information inference process in electronic word-of-mouth: An objectivity–subjectivity dichotomy perspective

We examined the actions of a customer when inferring product information from electronic word-of-mouth (eWOM) material at a website. We developed a customer purchase intention model and simulated various eWOM levels within this, adopting an objectivity–subjectivity dichotomy, and considering quality and preference as the major antecedents of customer purchase intention. We inferred the information that the customers had obtained from the eWOM by categorizing the customers’ responses. The eWOM was parameterized using mean and variance; products that were categorized into quality and preference goods. We considered four cases in which customers infer different product information and exhibit different reactions. Items for quality and preference goods were developed by using a card-sorting method. An experimental survey was conducted on 121 Korean Internet shopping mall users. The hypotheses were partially supported using a Partial Least Squares path comparison method. Overall, our study should provide guidance to firms in their managing eWOM systems by identifying how customers react to them at various levels.