Machine learning technology is recently being applied to various fields. However, in the field of online consumer conversion, research is limited despite the high possibility of machine learning application due to the availability of big data. In this context, we investigate the following three research questions. First, what is the suitable machine learning model for predicting online consumer behavior? Second, what is the good data sampling method for predicting online con-sumer behavior? Third, can we interpret machine learning’s online consumer behavior prediction results? We analyze 374,749 online consumer behavior data from Google Merchandise Store, an online shopping mall, and explore research questions. As a result of the empirical analysis, the performance of the ensemble model eXtreme Gradient Boosting model is most suitable for pre-dicting purchase conversion of online consumers, and oversampling is the best method to mitigate data imbalance bias. In addition, by applying explainable artificial intelligence methods to the context of retargeting advertisements, we investigate which consumers are effective in retargeting advertisements. This study theoretically contributes to the marketing and machine learning lit-erature by exploring and answering the problems that arise when applying machine learning models to predicting online consumer conversion. It also contributes to the online advertising literature by exploring consumer characteristics that are effective for retargeting advertisements.

Purpose: The purpose of this paper is to analyze the relationship between customer engagement in social media (CESM), brand equity and corporate performance and investigated whether these relationships differed according to cultural factors in the United States and South Korea.Design/methodology/approach: We collected customer engagement on social media data on Facebook and brand equity data from Interbrand for listed companies in the United States and Korea. A total of 405 data sets were analyzed by partial least squares structural equation modeling (PLS-SEM).Findings: Results revealed that CESM did not affect financial performance through a direct path but was found to have a positive indirect path via the mediation of brand equity. In addition, this relationship was found to differ between the United States and South Korea.Originality/value: This study contributed to the literature on social media and international management by verifying the relationship between CESM, brand equity and financial performance, and by presenting exploratory research results to ascertain if these relationships differ according to the cultural dimension of the country.

Purpose: The authors investigated the effects of the characteristics of reviews, reviewers and corporate factors on review helpfulness and assessed the role of culture in moderating these relationships.Design/methodology/approach: A research model was established based on the elaboration likelihood and information adoption models. To empirically analyze this research model, 10,611 TripAdvisor reviews from 9 countries were collected. In addition, a zero-inflated negative binomial model and multilevel analysis were employed in consideration of the data characteristics.Findings: The results revealed that review depth had a positive effect on review helpfulness, and review ratings and reviewer expertise had a negative effect. As a corporate characteristic, hotel size had a negative effect on review helpfulness. In addition, the effects of review rating, reviewer expertise and hotel rating exhibited significant differences based on the moderating effects of uncertainty avoidance and power distance level.Originality/value: The results of this study expand the review helpfulness literature by explaining the inconsistent findings of previous studies via cultural theory. In addition, past research in this field has mainly focused on analyzing only review and reviewer characteristics, while this study demonstrated that company size negatively affects review helpfulness based on the signaling theory. Finally, this study contributes to cultural comparison literature by discovering that the processing of review information by consumers differs according to their cultural background.

Purpose: This study analyzes the relationship between the characteristics of social media content, customer engagement (CE) and brand equity and investigates whether these relationships differ between national cultures.Design/methodology/approach: We collect data from a variety of sources, including Interbrand, Facebook and financial statements, to validate the research model using partial least squares structural equation modeling.Findings: The results revealed that owned media content had a stronger positive effect on CE than did earned media content. In addition, information richness was found to have a positive effect on CE, but links to additional information had a negative effect. In addition, CE positively affected brand equity. The national comparison analysis revealed a difference in the coefficients between the United States and Korea for most paths.Research limitations/implications: This study contributes to the relevant literature by finding evidence that OM has a stronger effect on CE than does EM. In addition, this study expands the related literature by clarifying the effects of information richness in a CE context and exploring differences determined by cultural dimensions. Most importantly, this study expands CE and international marketing literature by finding that the relationship between CE determinants and outcomes in a social media environment differs between national cultures.Originality/value: This study explores the relationship between CE and social media content, which has not been sufficiently investigated in previous studies, by collecting actual social media data. In addition, unlike previous survey-based studies, we find evidence that CE contributes to brand equity at a corporate level. Finally, our exploratory analysis indicates that the relationship between the characteristics of social media content, CE and brand equity differs between national cultures.

Purpose: This study is based on the heuristic-systematic model (HSM) to dynamically examine the effect of review variance on sales and the boundary conditions that mitigate this effect.Design/methodology/approach: Based on the theoretical domain of HSM, a conceptual model is proposed that analyzes the nonlinear relationship between review variance and sales and the interaction and motivation factors that moderate these relationships. Review data from websites targeting the film industry in the USA and South Korea (Korea) were collected to empirically analyze the authors' hypothesis, and panel regression analysis was used for confirmation.Findings: Moderated by interactive and motivational factors, review variance exhibits an inverse-U-shaped relationship with review variance. Specifically, as an interaction factor, review valence and owned social media (OSM) resulted in positive interaction effects, and as a motivation factor, the number of alternatives exhibited a positive interaction effect with review variance. The effect of review variance was less pronounced in the USA than in Korea.Originality/value: The study outcomes reveal a nonlinear relationship between review variance and sales, thus supporting the contradictory findings of previous studies. This study contributes to the literature by using the HSM as a theoretical framework to verify various HSM mechanisms using online review data. This exploratory study also contributes to the international marketing literature by showing that the effects of review variance vary across cultures.

Purpose: The purpose of this study is to analyze the effect on movie performance of the breadth and depth of consumer groups targeted by movies and to analyze the ways in which electronic word-of-mouth (eWOM) mediates these relationships.Design/methodology/approach: For empirical analysis, 45 days of sales and eWOM data for 63 movies released in Korea in 2017 were collected, and a panel regression analysis was conducted on a total of 2,835 data items. In addition, the analysis was rigorously verified through three robustness tests.Findings: The breadth and depth of consumer groups targeted by movies have a non-linear relationship with sales, and this relationship is mediated by the eWOM performance of social media websites. In addition, eWOM performance has a non-linear relationship with sales, and these effects differ depending on the type of eWOM platform involved.Originality/value: The effects of the breadth and depth of the consumer groups targeted by movies on eWOM performance and movie performance have not been sufficiently investigated. This paper expands on previous studies that reported a linear relationship between eWOM and sales by finding that the effects of consumer group breadth and depth on sales are not linear in terms of the mediation of eWOM performance. In addition, a new research direction is suggested by conceptualizing consumer group breadth and depth using eWOM data, on which basis the new concept of eWOM-to-viewing ratio (eWOM ratio) is proposed.