Attention Trajectories Predict Brand Choice

Modeling Eye Movements During Decision Making: A Review

“…Product-based processing involves acquisition of information on a single product across multiple attributes. It is a high-effort strategy which supports the integration of information into an overall expected value or utility (Martinovici, Pieters, & Erdem, 2021). Early process-tracing methods such as Mouselab, where participants open and close information cells on an electronic display, suggested that people first use by-attribute processing and then switch to by-product processing before making a choice (Bettman et al, 1998).…”

“…Recent models of preferential decision-making aim to predict future choice between multiple alternatives while endogenizing the complete eye-movement process. For example, Martinovici et al (2021) use not just the final fixations, as in research on the gaze cascade (Shimojo et al, 2003), or the sum of fixations as in aDDMs, but the entire trajectory of eye movements for each of the choice alternatives to predict preferential decision making in a naturalistic choice task. They develop a joint model of eye movements and choice outcomes that describes the gaze on product ROIs over time as a set of covarying higher-order polynomials.…”

“…(2) DDMs typically rely on the assumption that visual information uptake is uniformly distributed across alternatives and attributes (for an exception see Gluth et al, 2020). This assumption is at variance with evidence that attention tends to be directed to higher valued options or the emerging winner during choice tasks (Martinovici et al, 2021;Meißner, Musalem, & Huber, 2016;Pieters & Warlop, 1999;Shimojo et al, 2003).…”

“…For example, visual factors, which have a large impact on choice decisions (Orquin et al, 2021), are typically absent. Extant models do not account for consecutive refixations on the same object (Chandon et al, 2009;Krajbich et al, 2010;Martinovici et al, 2021;Yang et al, 2015), which is a striking characteristic of scan-paths across a wide range of tasks (Liechty et al, 2003;Musalem, Montoya, Meißner, & Huber, 2021;Rayner, 1998;van der Lans et al, 2008b).…”

Consumer search: What can we learn from pre-purchase data?

“…In the online environment, collecting eye movement data using a computer camera represents a less obtrusive option (Martinovici et al 2021;Ursu et al 2022). Similar to clickstream data, eyetracking data permits researchers to observe the identities and sequence of products a consumer searches.…”