No abstract

F irms are increasingly engaging with customers on social media. Despite this heightened interest, guidance for effective engagement is lacking. In this study, we investigate customers' compliments and complaints and firms' service interventions on social media. We develop a dynamic choice model that explicitly accounts for the evolutions of both customers' voicing decisions and their relationships with the firm. Voices are driven by both the customers' underlying relationships and other factors such as redress seeking. We estimate the model using a unique data set of customer voices and service interventions on Twitter. We find that redress seeking is a major driver of customer complaints, and although service intervention improves relationships, it also encourages more complaints later. Because of this dual effect, firms are likely to underestimate the returns on service intervention if measured using only voices. Furthermore, we find an "error-correction" effect in certain situations, where customers compliment or complain when others voice the opposite opinions. Finally, we characterize the distinct voicing tendencies in different relationship states, and show that uncovering the underlying relationship states enables effective targeting. We are among the first to analyze individual customer level voice dynamics and to evaluate the effects of service intervention on social media.

User profile is a summary of a consumer’s interests and preferences revealed through the consumer’s online activity. It is a fundamental component of numerous applications in digital marketing. McKinsey & Company view online user profiling as one of the promising opportunities companies should take advantage of to unlock “big data’s” potential. This paper proposes a modeling approach that uncovers individual user profiles from online surfing data and allows online businesses to make profile predictions when limited information is available. The approach is easily parallelized and scales well for processing massive records of user online activity. We demonstrate application of our approach to customer-base analysis and display advertising. Our empirical analysis uncovers easy-to-interpret behavior profiles and describes the distribution of such profiles. Furthermore, it reveals that even for information-rich online firms profile inference that is based solely on their internal data may produce biased results. We find that although search engines cover smaller portions of consumer Web visits than major advertising networks, their data is of higher quality. Thus, even with the smaller information set, search engines can effectively recover consumer behavioral profiles. We also show that temporal limitations imposed on individual-level tracking abilities are likely to have a differential impact across major online businesses, and that our approach is particularly effective for temporally limited data. Using economic simulation we demonstrate potential gains the proposed model may offer a firm if used in individual-level targeting of display ads. Data, as supplemental material, are available at http://dx.doi.org/10.1287/mksc.2015.0956 .

Consumers who are close to one another in a social network often make similar purchase decisions. This similarity can result from latent homophily or social influence, as well as common exogenous factors. Latent homophily means consumers who are connected to one another are likely to have similar characteristics and product preferences. Social influence refers to the ability of one consumer to directly influence another consumer's decision based upon their communication. We present an empirical study of purchases of caller ring-back tones using data from an Asian mobile network that predicts consumers' purchase timing and choice decisions. We simultaneously measure latent homophily and social influence, while also accounting for exogenous factors. Identification is achieved due to our dynamic, panel data structure and the availability of detailed communication data. We find strong influence effects and latent homophily effects in both the purchase timing and product choice decisions of consumers. This paper was accepted by Sandra Slaughter, information systems.

Platforms refer to intermediaries that facilitate economic interaction between two sets of agents wherein the decisions of one set of agents are likely to have an effect on the other via direct and/or indirect externalities. Given their nature, platforms need to find the appropriate balance between the competing objectives of agents and act as catalysts by facilitating the beneficial effects of externalities. In this paper, we discuss the current theoretical and empirical literature on two-sided platforms. We then identify three dimensions that offer opportunities to advance the empirical literature: (a) unanswered theoretical and conceptual questions, (b) data-related opportunities, and (c) methodological challenges.