Predicting consumer gaze hits: A simulation model of visual attention to dynamic marketing stimuli

Abstract

The purpose of the present study is to build and test a simulation model for the prediction of gaze hits in the context of dynamic marketing stimuli. Forecasting the attentional effect of dynamic stimuli is of particular interest when it comes to indirect forms of marketing communication such as sponsorship, product placement, or in-game-advertising. Based on large-scale eye tracking data an artificial neural network was trained, providing high predictive accuracy. The model's business applicability is demonstrated with the case of a soccer sponsorship, using media data and color features as model input. The study highlights the value of eye tracking data for the ex-ante valuation of visual communication stimuli which benefits marketing management at the initiation, implementation, and evaluation stages.