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.

PurposeThe 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/approachFor 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.FindingsThe 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/valueThe 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.