Do fMRI Data Improve Predictions of Product Adoption by Store Managers and Sales per Store of Consumer Packaged Goods?

This research examines whether functional magnetic resonance imaging (fMRI) data add predictive value beyond traditional market and survey data in forecasting two critical outcomes: (1) store manager adoption and (2) consumer sales of consumer packaged goods. Using data from a large retail chain, this study combines observable market variables, survey-based attitudes from a large representative consumer sample, and fMRI signals from a smaller convenience sample. Applying decision tree and least absolute shrinkage and selection operator (LASSO) regression approaches, the authors find that fMRI data enhance sales forecasts—particularly for more innovative products—while survey measures better predict store manager adoption. The research also quantifies the economic value of these improvements relative to data-acquisition costs, providing a framework for evaluating the return on investment of neuroforecasting tools. These findings clarify when neural measures add the most value over conventional analytics — particularly for innovative products at the consumer sales stage — with implications for product launch strategies and data investment decisions.