Semi-Supervised Response Modeling

Response modeling is concerned with identifying potential customers who are likely to purchase a promoted product, based on customers' demographic and behavioral data. Constructing a response model requires a preliminary campaign result database. Customers who responded to the campaign are labeled as respondents while those who did not are labeled as non-respondents. Those customers who were not chosen for the preliminary campaign do not have labels, and thus are called unlabeled. Then, using only those labeled customer data, a classification model is built in the supervised learning framework to predict all existing customers. However, often in response modeling, only a small part of customers are labeled, and thus available for model building, while a large number of unlabeled data may give valuable information. As a method to exploit the unlabeled data, we introduce semi-supervised learning to the interactive marketing community. A case study on the CoIL Challenge 2000 and the Direct Marketing Educational Foundation data sets shows that the transductive support vector machine, one of widely used semi-supervised models, can identify more respondents than conventional supervised models, especially when a small number of data are labeled. Semi-supervised learning is a viable alternative and merits further investigation.     

Maximizing Profits for a Multi-Category Catalog Retailer

It is a common trend in the retail industry for catalog retailers to mail multiple catalogs, each promoting different product categories. The existing catalog mailing models do not address the issue of optimizing multi-category catalog mailing. We address this research gap by introducing a model that integrates the when and what components of a customer's purchase decision into the how much component (number of catalogs) of a firm's cross-selling strategy. In addition to comparing the impact of category-specific versus full product catalogs in generating sales in a specific category, the study also finds relative impacts of various category-specific catalogs. We jointly estimate the probability of purchase and purchase amounts in multiple product categories by using multivariate proportional hazard model (MVPHM) and a regression based purchase amount model in a Hierarchical Bayesian framework. The model accounts for unobserved heterogeneity, and uses a control function (CF) approach to account for endogeneity in catalog mailing. The results from the Genetic Algorithm (GA) based optimization suggest that the catalog mailing policy as per the proposed model would be able to generate 38.4 percent more customer lifetime value (CLV) from a sample of 10 percent of the households as compared to the current catalog mailing policy of the retailer by reallocation of the catalogs across customers and mailing periods based on their propensity to buy.     

The influence of price and brand loyalty on store brands versus national brands

Abstract

This article investigates how price and brand loyalty of three frequently purchased product categories can influence the purchase decision process of store brands versus national brands. A multinomial logit model was constructed to analyse the data obtained from a consumer panel. The results confirmed that brand loyalty is the main variable which influences the purchase decision process of both national and store brands. The influence of price on the purchase decision process is product specific. There is a clear distinction between the buyer's profile of store brands and national brands. But there is no evidence of any correlation between demographic variables and national brands or store brands.     

Donor Segmentation: When Summary Statistics Don't Tell the Whole Story

Funding pressures amidst the slow economic recovery from the late-2000's recession have forced universities, as well as other not-for-profit organizations, to increase the volume and sophistication of their direct marketing activities. The efficiency of direct marketing strategies is linked to an organization's ability to effectively target individuals. In this paper, we present a finite-mixture model framework to segment the alumni population of a university in the midwestern United States.Much of the research on customer segmentation summarizes response data (e.g., purchase and contribution histories) via recency, frequency and monetary value (RFM) statistics. Individuals sharing similar RFM characteristics are grouped together; the rationale being that the best predictor of future behavior is past behavior. Summary statistics such as RFM, however, introduce aggregation bias that mask the dynamics of purchase/contribution behavior. Accordingly, we implement latent-class segmentation models where alumni are classified based on how an individual's contribution sequence compares to those of other individuals. The framework's capability to process contribution sequences, i.e., longitudinal data, provides fundamental new insights into donor contribution behavior, and provides a rigorous mechanism to infer and segment the population based on unobserved heterogeneities (as well as based on other observable characteristics). Specifically, we analyze Markov mixture models to segment alumni based on contribution-behavior patterns, under the assumption of serially-dependent contribution sequences. We use the expectation–maximization algorithm to obtain parameter estimates for each segment. Through an extensive empirical study, we highlight the substantive insights gained through the processing of the full contribution sequences, and establish the presence of three distinct classes of alumni in the population (each with a discernible contribution pattern). The proposed framework, collectively, provides a basis to tailor direct marketing policies to optimize specific performance criteria (e.g., profits).     

Factors influencing consumers' purchase decision-making in O2O business model: Evidence from consumers' overall evaluation

Online-to-offline (O2O) has become a rapidly growing e-commerce model worldwide, but the factors influencing consumers' purchase decision-making have not been examined well. After exploring the working mechanism of the O2O model, we extract eleven indexes of consumers' overall evaluation in the O2O model with Crawlzilla and R techniques. Social network analysis (SNA) is adopted to build social networks reflecting consumers' overall evaluation in the O2O model. Based on the modified social network and the extracted subgraph, this study (N = 768) reveals consumers' overall evaluation behavior patterns in the O2O model by calculating network density, central potential, edge betweenness. The results show that shoppers overall evaluate the eleven indexes, especially perceived product quality, online product price, promotion intensity, business reputation, and product brand, which reflects the significant associations between the indexes. Among all the eleven evaluation indexes, perceived product quality, online product price, and business reputation dominate consumers’ decision-making behavior. When making purchase decisions, consumers not only overall consider online product price, perceived product quality, and business reputation but also balance perceived product quality, business reputation, and promotion intensity. Finally, we make some suggestions on marketing strategy for e-commerce companies.     

RFM-based repurchase behavior for customer classification and segmentation

Customer behavior modeling and classification are well-studied areas for applications in retail. Past studies implemented the purchase behavior modeling based on the physical behavior of a subject. In this research, we apply the recency, frequency, and monetary (RFM) model and data modeling techniques to detect behavior patterns for a customer. Each transaction attributed to a customer is part of one's behavior, and an instance of the feature vector, it is modeled on a set of transactions to constitute repurchase behavior. The proposed scheme is validated by simulating a publicly accessible real-world data set with a need-tailored multi-layer perceptron (MLP) and also support vector machine (SVM) and decision tree classification (DTC) methods. The experiments yield a high customer classification rate of more than 97% for the different numbers of the customers. Empirical analysis shows that eight transactions are sufficient to classify a customer with high accuracy.     

Joint modeling of effects of customer tier program on customer purchase duration and purchase amount

Nowadays, many supermarkets implement a customer tier program to increase their profits because it is expected to raise customers' willingness to purchase by setting thresholds. However, designing an appropriate program is difficult because each customer's heterogeneous purchase behavior is difficult to capture. Therefore, we simultaneously modeled purchase frequency and amount through a marked point process approach while considering program effects and customer characteristics. The results clarified that the points pressure effect was particularly strong among customers who originally visited the store infrequently and had not attained the threshold set up in the customer tier program many times in the past. In addition, we found that the three-tier customer tier program was superior to the two-tier program with respect to the operating income in supermarkets.     

Cross-decision social effects in product adoption and defection decisions

Researchers and practitioners have long been aware of the capacity to use information on consumers' product adoptions and defections to forecast the adoption and defection behavior of others in their social networks. Yet, herein, we suggest that such information still holds substantial untapped predictive potential. Specifically, this paper is the first to define and investigate cross-decision social effects, i.e., the effects of customer defections on network neighbors' adoption decisions, and the effects of customer adoptions on network neighbors' defection decisions. We incorporate these effects into a conceptual framework that enables us to explore them concurrently with same-decision social effects (the effects of adoptions on adoptions and of defections on defections), which have been researched extensively. We develop a multi-event hazard model to describe this framework, and estimate it using two unique data sets on a communication network and on adoption and defection dates for a mobile add-on. We obtain strong empirical evidence for negative cross-decision social effects that are larger for strong ties than for weak ties.     

Internal Relationship Management

SUMMARY

In the quest for sustainable competitive advantage, managers have sought to differentiate themselves through a customer (as opposed to product) focus. This has given rise to successive strategies designed to improve the customer experience (e.g., objective quality, service quality, customer satisfaction, customer retention, customer loyalty, etc.). The problem, however, is that a satisfied, loyal customer who is persuaded to consistently buy a firm's product or service over and over again because of its quality can be and often is unprofitable. Therefore, using such strategies does not guarantee increased profits. As a result, firms will increasingly rely on the measurement and management of customers' lifetime values to guide their customer loyalty efforts.     

A multi-category customer base analysis

Customer base analysis is an essential tool to measure and develop relationships with customers. While various models have been proposed in a noncontractual setting, they focus primarily on analyzing transactional patterns associated with a single product category or a firm-level activity, such as the times at which purchases are made at a particular retailer. This research proposes a modeling framework for customer base analysis in a multi-category context. Specifically, we model the time between a customer's purchases at the firm and the product categories that comprise her shopping basket arising from multi-category choice decisions. The proposed model uses a latent space approach that parsimoniously captures the dynamics of multi-category shopping behavior due to the interplay between purchase timing and shopping basket composition. We also account for interdependence among multiple categories, temporal dependence across category choices, and latent customer attrition. Using category-level transaction data, we show that the proposed model offers excellent fit and performance in predicting customer purchase patterns across multiple categories. The forecasts and inferences afforded by our model can assist managers in tailoring marketing efforts across categories.     

The Mediating Role of Customer Relationship on the Social Media Marketing and Purchase Intention Relationship with Special Reference to Luxury Fashion Brands

The reach of internet technology and social media has opened abundance of opportunities for marketers as well as for consumers across the globe. To anticipate future purchase behavior of consumers, marketers are not leaving any stone unturned. The main objective of this study is to investigate the direct and indirect impacts of social media marketing activities (entertainment, customization, interaction, word of mouth, and trend) on consumers' purchase intentions in luxury fashion brands. This study employed higher order Structural Equation Modeling to test the study model with (n = 243) sample data. We found positive significant impacts of social media marketing and customer relationships on consumers' purchase intentions. In addition, our study model confirmed full mediation of customer relationships in the relationship between social media marketing and consumers' purchase intentions. Based on our research findings, we strongly recommend that marketers of luxury fashion brands engage in social media marketing activities to provide value to customers.     

The Showrooming Phenomenon: It's More than Just About Price

This paper examines the factors that influence competitive showrooming, whereby consumers visit an offline retail store to gather information but make their purchase online at a competing retailer. We survey 556 respondents to study how the benefits and costs of showrooming influence the consumer's decision to showroom. Not surprisingly, we find that expected average price savings from showrooming are positively associated with showrooming. In addition, however, the perceived dispersion in online prices is also positively related to showrooming. Moreover, we find that non-price factors play a key role in consumers' showrooming decisions: perceived gains in the quality of the product purchased when showrooming (measured as the fit with a consumer's need) and waiting time for service in the brick-and-mortar store are positively associated with showrooming. Online search costs are negatively related to showrooming. Time pressure that consumers face when shopping is negatively associated with their propensity to showroom. We discuss implications for researchers and retail managers. For example, managers of offline retail stores can curtail showrooming by increasing the number of sales personnel available in-store instead of providing currently employed personnel with more training. To encourage showrooming, managers of online retailers should make it easier for the customer to search online.     

Customers' judgment of the customer service in appliance sales departments in an emerging economy

Evidence that consumers in emerging economies are more tolerant of ineffective customer service (CS), instigated an investigation into controllable elements of the service offering in a specific context in South Africa, namely, appliances sales departments in retail stores. The research aimed to identify possible shortcomings in CS amidst evidence that consumers are exposed to sophisticated merchandise that they have limited experience and understanding of. The intention was to suggest initiatives to augment the service offering so that it becomes more conducive for informed, responsible buying decisions. Household appliances represent a category of complex, durable and expensive merchandise that require more extensive information search before concluding buying decisions. A survey was done in 2007 through a pre‐tested structured questionnaire. Several branches of five prominent department stores were involved through liaison with industry. A store intercept method was used to recruit respondents: 296 questionnaires were filled in on the spot under supervision. Three sections of the questionnaire are relevant for this report: (1) consumers' satisfaction with CS; (2) a product knowledge test; and (3) demographic information. Factor analysis revealed a reduction of the original five elements of CS in the scale to three distinct elements that were labelled Personnel, Processes and Value for Money, and Product Presentation. The simpler scale suggests a less intricate judgment of CS in the context of this research. Means indicated that consumers were generally satisfied with all elements of CS, i.e. the service offering coincided with their expectations. Analysis of variance indicated no significant differences in the interpretation of any of the elements of CS by gender. A significant inverse relationship between satisfaction with CS and years of experience occurred for respondents with more than 25 years of experience in terms of Personnel (Element 1) and Processes and Value for Money (Element 2). Findings of the product knowledge tests were meant to verify consumers' CS judgments. However, scores were disappointingly low for all appliances across all respondent categories. Consumers' product knowledge could therefore not have supported informed buying decisions, despite prior experience and the opportunity to acquire additional product information during the in‐store encounter. Consumers' positive CS judgments suggest that they not necessarily realize their lack of crucial product knowledge. In the interest of informed and responsible buying decisions that have consequences for proper use and maintenance of appliances in the long term, retail stores that serve a broad customer base are encouraged to attend to in‐store customer assistance during the pre‐purchase phase, notwithstanding positive CS judgments. Non‐formal consumer education by competent, well‐trained salespeople is recommended to encourage evaluative rational product judgments. It is also suggested that store displays are designed to encourage consumers to be more inquisitive during store visits.     

Will he buy a surprise? Gender differences in the purchase of surprise offerings

In the last few years, retailers have introduced numerous products that intentionally conceal some information from the consumer at the time of decision making. While prior research has identified contexts in which customers are attracted to such offerings in the aggregate, heterogeneity in customer proclivities is not well-understood. In the present paper, we examine the effect of gender on choice of surprise (vs. certain) offerings at the point of purchase. We propose and find that, on average, men are less likely to opt for a surprise offering compared to women. We examine multiple mechanisms that could explain this effect – emotionality, desire for exploration, and desire for control – and find the strongest support for the latter, demonstrating that it is men's stronger desire for control over the purchase outcome that drives their preference for certain (vs. surprise) offerings. Consequently, contexts or product categories that make it acceptable for men to let go of control attenuate the observed gender difference. We present data from a travel services firm, an online product catalog, and both field and lab studies, providing robust support for this theory across multiple product categories and participant populations. This work concludes with a discussion of the potential boundary effects of the observed gender difference, a managerial roadmap that delineates the ways in which marketers can offer surprise offerings more fruitfully to both men and women, and recommendations for future research.     

Cross-selling across stores or within a store? Impacts of cross-buying behavior in online shopping malls

Abstract

This study investigates the impacts of cross-buying behavior in an online shopping mall where customers can purchase from additional product categories from various independent stores. We focus on the extent to which store loyalty and relationship duration moderate the cross-buying effects on three behavioral traits: customers’ purchase rate, lifetime duration, and spending. The results reveal that customers who engage in cross-buying more intensely purchase more frequently, have longer expected lifetime duration, and spend higher amounts in each transaction. The impacts on purchase frequency and customer retention are even greater for customers who exhibit higher behavioral loyalty toward some stores. However, store loyalty is found to weaken the association between cross-buying and average spending. Further, relationship duration appears to weaken the effects of cross-buying on purchase rate and spending. These results provide new insights into the impacts of cross-buying on customer value as well as managerial implications for shopping mall owners.     

Measuring the impact of online reviews on consumer purchase decisions – A scale development study

Consumers' exposure to online reviews influences their online retail shopping behavior. They search for reviews while evaluating products for purchase decisions. Past studies have indicated that online reviews affect the credibility and trust of the sellers and the products they sell on online platforms. Keeping this in view, the current paper aims to develop and validate a scale to understand the impact of online reviews on consumer purchase decisions. Data were collected from 431 young online shoppers for this research. The initial exploratory factor analysis (EFA) results helped identify four factors, viz. source credibility, volume, language and comprehension, and relevance which constitute the scale. The scale was validated by confirmatory factor analysis (CFA). The study's findings fill the gap of having a standardized scale that online retailers can use as indicators to assist consumers in their online decision-making. The discussions and implications support consumers' susceptibility to online reviews, an essential source for product and brand information in facilitating online consumers' purchase decisions.     

Evidence Supporting the Importance of Brands in Marketing Computer Products

ABSTRACT

For convenience store (c-store) management to be truly customer-focused, they must listen to their customers and provide the products that meet customers' needs. This study investigates one aspect of c-store customer satisfaction, the product mix. The purpose of this paper is to investigate c-store customers' perceptions of product offerings to expand the c-store's product mix and in turn increase customer satisfaction. Fourteen products were examined. Of the fourteen, three were rated very likely to be purchased: postal services, home style meals, and a salad bar. Differences in preference were found between gender and marital status. Men and single customers had higher purchase intentions for the home style meals than women and married customers. Suggestions for future research are provided.     

Modeling and Promoting Organic Food Purchase

This study aims at enhancing organic food product (OFP) purchase by identifying customer segments based on their knowledge and attitude related to organic food along with their demographic profile. Two scales for measuring Knowledge and Attitude related to organic food were developed to measure their levels. The scales have covered six dimensions of organic food: Healthy, Eco-friendliness, Price, Availability, Certification, and Brand. After identifying the customer segments, each segment was further segmented based on their media consumption behavior. Hierarchical followed by K means cluster analysis resulted to six distinct segments with their corresponding subsegments. Cluster analysis was again performed for each customer segment, and a media selection method (MSM) was evolved to effectively communicate with OFP customers. These methods can guide marketers in devising an appropriate communication plan for enhancing OFP purchase.