Preference-based serial decision dynamics: your first sushi reveals your eating order at the sushi table

Abstract

In everyday life, we regularly choose among multiple items serially such as playing music in a playlist or determining priorities in a to-do list. However, our behavioral strategy to determine the order of choice is poorly understood. Here we defined 'the sushi problem' as how we serially choose multiple items of different degrees of preference when multiple sequences are possible, and no particular order is necessarily better than another, given that all items will eventually be chosen. In the current study, participants selected seven sushi pieces sequentially at the lunch table, and we examined the relationship between eating order and preference. We found two dominant selection strategies, with one group selecting in order from most to least preferred, and the other doing the opposite, which were significantly different from patterns generated from a random strategy. Interestingly, we found that more females tended to employ the favorite-first rather than favorite-last strategy. These two choice sequences appear to reflect two opposing behavioral strategies that might provide selective advantages in their own right, while also helping to provide solutions to otherwise unconstrained problems.

Figure 1. Relationship between eating order and the degree of preference.

Subject number matrix (A) and Saliency matrix (B). The horizontal axis represents the eating order, and the vertical axis represents the degree of preference. Each element of the matrix represents (A) the number of subjects making the particular choice and (B) 1– p, where p is the probability that the number of subjects in the matrix cell resulted from random order selections; *p<0.05; **p<0.01.

Figure 2. Comparison of saliency maps with random sequences.

(A–B) Saliency maps for Groups 1 and 7. Each element of the matrix represents 1– p, where p is the probability that the number of subjects derived from random order selections; *p<0.05; **p<0.01. Thin white lines demarcate the confining condition for each group; no subject can be located in such areas. (C). Mean slope of the linear regression relating eating order to preference. The slope of Group 1 is significantly higher than that of its random pair, whereas Groups 5, 6, and 7 show significantly lower slopes (**p<0.01). (D). Number of participants in each group. The Kolmogorov-Smirnov test was applied to test for an uneven distribution, p<0.01 (male), p<0.001 (female).