PREDICTING INDIVIDUAL- AND MARKET-LEVEL
OUTCOMES
The potential benefits of neuroscience research to marketing are arguably the most evident in efforts to leverage the predictive power afforded by incorporating neural data in models of marketing-relevant behavior. Recent advances in neuroimaging methods and analyses have enabled researchers in consumer neuroscience the opportunity to generate consumer insights and to inform real-world marketing decisions with practical and economically significant consequences. In particular, the notion that neural data collected on a relatively small sample of participants can predict choices in real-world contexts holds tremendous promise for marketers. In this special issue, two articles use EEG to make predictions about product choices. The first, by Telpaz, Webb, and Levy (2015), applies EEG to a small group of participants and shows that changes in amplitude of the N200 component and in theta band power during passive viewing of consumer products reliably predict future choices of consumer products. This is the first EEG study to predict product choices without eliciting any responses whatsoever from consumers. It has clear implications for marketing insofar as EEG is much more cost effective, widely accessible, and portable than fMRI. Boksem and Smidts(2015) also use EEG and analyze amplitudes of beta and gamma oscillations of a relatively small group of consumers as they view movie trailers. The authors then use these neural measures to predict stated individual-level preferences as well as movie sales at the population level. They find a significant increase in predictive power of the neural measures, beyond self-reported preference measures, to predict people’s willingness to pay and market-level sales outcomes. Thus, brains can help predict box office sales.Finally, the article by Venkatraman et al. (2015) directly compares the efficacy of six behavioral and neurophysiological methods in assessing consumers’ responses to 30- second television ads. The methods they compare span a wide range: traditional self-reports, an implicit association test, eye tracking, biometrics, EEG, and fMRI. They further compare the six measures in terms of how well they predict aggregate market-level advertising elasticities. They find that fMRI explains the most variance in advertising elasticities beyond the baseline traditional measures. Analyses of the 30-second advertising time intervals may have placed biometric and EEG measures at a disadvantage because those methods are better than fMRI for rapid subsecondresolutions. The authors note that biometric and EEG measures may be more effective for understanding millisecondby- millisecond or scene-by-scene resolution of ads.