Data mining in business services

Data mining applies traditional statistical tools as well as artificial intelligence algorithms to the analysis of large datasets. Data mining has proven very effective in many fields, including business. This paper reviews applications of data mining relevant to the service industry, and demonstrates primary business functions and data mining methods. Typical industry data mining process is described, analytic tools are reviewed, and major software tools noted.     

Comparison of customer response models

Segmentation of customers by likelihood of repeating business is a very important tool in marketing management. A number of approaches have been developed to support this activity. This article reviews basic recency, frequency, and monetary (RFM) methods on a set of data involving the sale of beef products. Variants of RFM are demonstrated. Classical data mining techniques of logistic regression, decision trees, and neural networks are also demonstrated. Results indicate a spectrum of tradeoffs. RFM methods are simpler, but less accurate. Considerations of balancing cell sizes as well as compressing data are examined. Both balancing expected cell densities as well as compressing RFM variables into a value function were found to provide more accurate models. Data mining algorithms were all found to provide a noticeable increase in predictive accuracy. Relative tradeoffs among these data mining algorithms in the context of customer segmentation are discussed.     

企业与消费者品牌互动认知差异探析

企业与消费者之间的互动是品牌建设的重要方式,但调查数据显示了目前企业与消费者在品牌互动态度、内容、行为及评价认知等方面存在着显著差异,严重影响了企业品牌建设的效果。本文认为,要缩小企业与消费者品牌互动认知的差异,需要企业和消费者双方都能对自身的角色和行为进行合理和有效的定位。     

Customer relationship management in retailing: A content analysis of retail trade journals

The purpose of this research was to increase knowledge and understanding of how retailers use business intelligence and data mining tools to implement customer relationship management (CRM) in retailing. Specific objectives were to (1) identify organization and infrastructure requirements for CRM effectiveness, (2) identify CRM objectives and goals of retail companies, (3) identify data mining tools utilized by retailers to perform CRM functions, and (4) identify CRM strategies used by retail companies. A keyword search within business databases using CRM and CRM identified publications with CRM content. Content analysis was used on articles (N=149) drawn from Stores, Chain Store Age, Harvard Business Review, and Retail Forward over a 5 year period (2000–2005). Selected articles were stored as text files in QDA Miner, a computerized qualitative analysis tool. Key organization/infrastructure needs emerged focusing on data structure, organizational systems, technology structure, and data accessibility. Retailers goals/objectives and strategies focused on marketing, customer service, understanding customers through data analysis and increasing acquisition and retention through customer loyalty programs. Data mining tools identified supported marketing and customer analysis efforts. Findings provide insight into the challenges retailers face as they implement a more customer-centric business strategy.     

A hybrid data mining model of feature selection algorithms and ensemble learning classifiers for credit scoring

Data mining techniques have numerous applications in credit scoring of customers in the banking field. One of the most popular data mining techniques is the classification method. Previous researches have demonstrated that using the feature selection (FS) algorithms and ensemble classifiers can improve the banks' performance in credit scoring problems. In this domain, the main issue is the simultaneous and the hybrid utilization of several FS and ensemble learning classification algorithms with respect to their parameters setting, in order to achieve a higher performance in the proposed model. As a result, the present paper has developed a hybrid data mining model of feature selection and ensemble learning classification algorithms on the basis of three stages. The first stage, as expected, deals with the data gathering and pre-processing. In the second stage, four FS algorithms are employed, including principal component analysis (PCA), genetic algorithm (GA), information gain ratio, and relief attribute evaluation function. In here, parameters setting of FS methods is based on the classification accuracy resulted from the implementation of the support vector machine (SVM) classification algorithm. After choosing the appropriate model for each selected feature, they are applied to the base and ensemble classification algorithms. In this stage, the best FS algorithm with its parameters setting is indicated for the modeling stage of the proposed model. In the third stage, the classification algorithms are employed for the dataset prepared from each FS algorithm. The results exhibited that in the second stage, PCA algorithm is the best FS algorithm. In the third stage, the classification results showed that the artificial neural network (ANN) adaptive boosting (AdaBoost) method has higher classification accuracy. Ultimately, the paper verified and proposed the hybrid model as an operative and strong model for performing credit scoring.     

Predicting direct marketing response in banking: comparison of class imbalance methods

Customers’ response is an important topic in direct marketing. This study proposes a data mining response model supported by random forests to support the definition of target customers for banking campaigns. Class imbalance is a typical problem in telemarketing that can affect the performance of the data mining techniques. This study also contributes to the literature by exploring the use of class imbalance methods in the banking context. The performance of an undersampling method (the EasyEnsemble algorithm) is compared with that of an oversampling method (the Synthetic Minority Oversampling Technique) in order to determine the most appropriate specification. The importance of the attribute features included in the response model is also explored. In particular, discriminative performance was enhanced by the inclusion of demographic information, contact details and socio-economic features. Random forests, supported by an undersampling algorithm, presented very high prediction performance, outperforming the other techniques explored.     

面向AFH客户分类主题的数据仓库的构建

近年来,随着客户关系管理（CRM）在商业运作中的巨大成功,其管理理念及价值被越来越多的企业所重视。在电子商务环境下,一对一营销正在受到企业的青睐。以客户为中心的思想,要求企业要能够有效地获取客户的各种信息,识别客户与企业之间的关系。文章在分析数据仓库特点的基础上,以客户平均购买额（A）、购买频率（F）和客户保持时间（H）作为客户价值细分变量,实例化构建了某食品连锁销售企业面向AFH客户分类主题的数据仓库。应用结果表明,新的AFH客户分类模型具有很强的表征性,能充分反映客户的当前价值（贡献度）和增值潜力（忠诚度）,能为企业提供有效的决策支持信息。     

基于商业智能的CRM

基于商业智能的CRM能实现数据分析和知识发现 ,可帮助企业将其所掌握的客户数据转换成客户知识 ,这对企业制订客户发展策略将起到关键作用 ,并将极大地提高企业决策能力、决策效率及决策正确性 ,针对不同客户提供不同的服务     

第四方共享物流解决方案综合评价分析方法——基于香农熵与变精度粗糙集

传统共享物流服务模式主要关注供应链局部环节物流设施设备的共用共享,所得出的往往是相对于供应链端到端视角的局部最优解。从全局优化角度寻找能够满足终端客户时效、经济、质量目标要求的共享物流解决方案,对实现供应链服务各参与方利益最大化具有重要价值。为避免先验知识与主观因素影响,确保共享物流解决方案选择的客观性,有效指导货主、收货人和物流服务提供商实现多赢,可从第四方物流视角出发,构建共享物流端到端多因素评价指标体系,进而基于变精度粗糙集、香农熵和遗传算法进行端到端共享物流解决方案综合评价分析。案例研究结果显示,在一级指标中,仓储运输资源整合共享能力、服务可靠性及一致性、国际化及智慧化水平的相对重要性程度更高;在二级指标中,跨主体物流系统集成能力、为客户提供增值服务的能力、可使用的仓储资源等相对重要性程度更高。为制定适合企业需要的共享物流解决方案,相关货主企业可利用上述综合评价模型和算法编制大数据分析软件,并结合不同物流服务提供商的时间序列数据和截面数据,对各潜在物流服务提供商综合能力进行评价,对有效决策规则进行筛选和挖掘。     

Data mining in road crash analysis: the context of developing countries

The recent advancements in the field of data mining have made vast progress in extracting new information and hidden patterns from large datasets which are often overlooked by the traditional statistical approaches. These methods focus on searching for new and interesting hypothesis which were previously unobserved. Road safety researchers working with the crash data from developed world have seen encouraging success in obtaining new insight into crash mechanism through data mining. An attempt was made in this study to apply these advance methods and evaluate their performance in manifesting crash causes for Bangladesh. The study applies hierarchical clustering to identify hazardous clusters, random forest to find important variables explaining each of these clusters, and classification and regression trees to unveil their respective crash mechanisms for the road crash data of Bangladesh. The results identified several new interesting relationships and acknowledged issues related to quality of data.     

All That Glitters is Not Gold: Digging Beneath the Surface of Data Mining

This article develops a more comprehensive understanding of data mining by examining the application of this technology in the marketplace. In addition to exploring the technological issues that arise from the use of these applications, we address some of the social concerns that are too often ignored.As more firms shift more of their business activities to the Web, increasingly more information about consumers and potential customers is being captured in Web server logs. Sophisticated analytic and data mining software tools enable firms to use the data contained in these logs to develop and implement a complex relationship management strategy. Although this new trend in marketing strategy is based on the old idea of relating to customers as individuals, customer relationship management actually rests on segmenting consumers into groups based on profiles developed through a firm's data mining activities. Individuals whose profiles suggest that they are likely to provide a high lifetime value to the firm are served content that will vary from that which is served to consumers with less attractive profiles.Social costs may be imposed on society when objectively rational business decisions involving data mining and consumer profiles are made. The ensuing discussion examines the ways in which data mining and the use of consumer profiles may exclude classes of consumers from full participation in the marketplace, and may limit their access to information essential to their full participation as citizens in the public sphere. We suggest more ethically sensitive alternatives to the unfettered use of data mining.     

The Role of Business and Friendships on WeChat Business: An Emerging Business Model in China

ABSTRACT

WeChat business is an emerging way of doing business in China, which can be considered as a marriage between traditional e-business and social networking communications. In WeChat business, firms have developed customer relationships along two distinct ways: business relationships and friendships. However, research on the combination of business relationships and friendships is relatively nascent, and there are contradictory findings. In this study, we examine the effectiveness of the two relationship strategies using data from a field experiment through the WeChat platform by an apparel firm. Results from the field experiment suggest that development of friendships with new customers can help the strategy of developing business relationships; but developing friendships and business relationships with experienced customers negates each other. The study contributes to the literature on relationship marketing and role theory, and helps WeChat managers clarify how new social networking relationships with customers can be effectively leveraged.     

A Preliminary Study of Fintech Industry: A Two-Stage Clustering Analysis for Customer Segmentation in the B2B Setting

ABSTRACT

This practitioner note proposes a new approach considering two-stage clustering and LRFMP model (Length, Recency, Frequency, Monetary and Periodicity) simultaneously for customer segmentation and behavior analysis and applies it among the Iranian Fintech companies. In this practitioner note, the K-means clustering algorithm and LRFMP model are combined in the customer segmentation process. After initial clustering, for a better understanding of valuable customers, additional clustering is implemented in segments that needed further investigation. This approach contributes to a better interpretation of different customer segments. Customer segments, consisting of 23524 business customers are analysed based on their characteristics and appropriate strategies are recommended accordingly. The first stage clustering result shows that customers are best segmented into four groups. The first and fourth segments are clustered again and the final 11 groups of customers are determined. This note provides a systematic and practical approach for researchers and practitioners for segmentation, interpretation, and targeting of customers especially in the B2B setting and the Fintech industry and helps managers to make effective marketing strategies and enhance customer relationship and marketing intelligence.     

Cluster Analysis of Smart Metering Data

The introduction of smart meter technology is a great challenge for the German energy industry. It requires not only large investments in the communication and metering infrastructure, but also a redesign of traditional business processes. The newly incurring costs cannot be fully passed on to the end customers. One option to counterbalance these expenses is to exploit the newly generated smart metering data for the creation of new services and improved processes. For instance, performing a cluster analysis of smart metering data focused on the customers’ time-based consumption behavior allows for a detailed customer segmentation. In the article we present a cluster analysis performed on real-world consumption data from a smart meter project conducted by a German regional utilities company. We show how to integrate a cluster analysis approach into a business intelligence environment and evaluate this artifact as defined by design science. We discuss the results of the cluster analysis and highlight options to apply them to segment-specific tariff design.     

基于谱聚类的用户关联关系挖掘

为了从用户地理空间分布数据中挖掘用户间关联关系,提出了一种基于谱聚类的关联关系挖掘算法。首先定义了关联度,用以衡量用户之间空间分布的相似性,基于关联度构造相似矩阵,再利用谱聚类方法对用户进行聚类分析,聚类结果表征了用户的关联关系。采用Silhouette指标和聚类准确率来衡量用户关系挖掘质量,同时与传统的K-Means方法进行了比较,通过真实数据集实验,结果表明该算法在实验数据集上能达到90%以上的聚类准确率,证明方法有效、可行。     

Customer portfolio composition and customer equity feedback effects: Student diversity and acquisition in educational communities

Researchers in marketing have long recognized that current populations of customers can influence the behavior of prospective customers. This paper draws on existing marketing theories to empirically examine how changes in student body demographic segments influence future demand for MBA programs. Using a longitudinal analysis of data spanning 18 years, we find that higher proportion of female students leads to significant increases in future applications. This implies a marketing rationale for business schools in encouraging gender diversity. In contrast, we find evidence of prejudice towards minority and international students among business school applicants. We discuss the results of the analysis in the context of the current affirmative action debate and changes in demographic trends.     

A novel framework for customer complaint management

Complaining is one option available to customers to express their dissatisfaction with inadequate services. Their complaints contain valuable information for service providers to improve customer relationships and operational quality, which can ultimately enhance business profitability. Customer complaints are frequently handled at the individual level, however, which addresses the symptoms rather than the causes of customer dissatisfaction. This paper presents a framework integrating a decision tree approach, a common data mining tool, into Six Sigma methodology to analyze customer complaints in aggregate and improve service quality by identifying and addressing the underlying causes of failed service. A case study of a restaurant chain was used to demonstrate the effectiveness of the proposed framework. The results indicated a significant (60%) decrease in the number of customer complaints received. Subsequent long-term benefits can be expected.     

物流企业CRM与数据挖掘技术

客户关系管理（CRM）不仅是一种管理理念,也是一种旨在改善企业与客户之间关系的新型管理机制,还是一种管理软件和技术。推行客户关系管理是物流企业获得顾客、增强市场竞争力的重要途径。有效的客户关系管理离不开客户数据分析,而数据挖掘则是进行客户数据分析的基本技术和方法。数据挖掘技术为物流企业CRM的成功提供了有力的技术保障。     

The Role of External Relationships for LSP Innovativeness: A Contingency Approach

Innovativeness is key to the success of logistics service providers (LSPs) and as LSPs often lack competencies for innovation internally, external relations as sources to acquire knowledge relevant for innovation are important. To the authors' knowledge, there is no research identifying the relevant knowledge sources for LSP innovativeness. Based on contingency theory, we develop a conceptual model on the relevance of different external relations in the context of the innovation focus of the LSP. Thus, we extend insights from previous studies that have only discussed the benefits of external knowledge acquisition in general and outline how to use existing business relations of an LSP to facilitate different types of innovation. The hypothesized model is tested based on survey data from 201 LSPs using structural equation modeling. The findings support the model and outline that better relationships with external service firms or other LSPs are not important for internal process improvements and innovations for existing customers, but very valuable for innovations targeting new customer business, while good relations to customers even show a slight tendency to hamper the development of innovations for new customer business. In addition, it is shown that innovativeness is a strong driver of LSP firm performance.