Behavioral cues help predict impact of advertising on future sales

Advertising aims to influence consumer preferences, appraisals, action tendencies, and behaviour in order to increase sales. These are all components of emotion. In the past, they have been measured through self-report or panel discussions. While informative, these approaches are difficult to scale to large numbers of consumers, fail to capture moment-to-moment changes in appraisals that may be predictive of sales, and depend on verbal mediation. We used webcam technology to sample nonverbal responses to television commercials from four product categories in six different countries. For each participant, head pose, head motion, and smiling were automatically measured at each video frame and aggregated across subjects. Dynamic features from the aggregated series were input to simple linear ensemble classifier with 10-fold cross-validation to predict product sales. Sales were predicted with ROC AUC= 0.737, 95% CI [0.712,0.762] and were highly consistent among product categories. ROC AUC for product categories varied by less than 1%. Variation was found among countries. Highest results were found for US and France (ROC AUC = 0.82 and 0.86, respectively) and lowest for Australia (ROC AUC = 0.69). In comparison with previously reported results using static features, models using dynamic features yielded higher performance and greater consistency among product categories. These findings support the feasibility, efficiency, and predictive validity of sales predictions from large-scale sampling of viewers’ moment-to-moment responses to commercial media.