Synthesizing Winning Strategies: What Differentiates Experienced Designers in Crowdsourcing Markets?

Abstract

Prior studies of online crowdsourcing platforms have examined participants’ behaviors and found that experienced designers are more likely to win in crowdsourcing contests. However, what gives experienced designers an edge in these contests is not well understood. Our study seeks to understand what differentiates experienced designers from other participants, with a particular focus on how they leverage information in open design contests. We use a large-scale empirical analysis employing deep-learning algorithms and find that, while experienced designers are similar to less-experienced designers in a number of ways, experienced designers are more adept at integrating information from several prior highly-rated submissions from other designers within a contest, while less-experienced designers are more likely to excessively imitate individual prior highly-rated submissions. We also find that experienced designers whose submissions are closer in similarity to a synthesized image of several highly-rated prior submissions, are more likely to win. Our results are consistent with prior work on recombinant innovations which finds that a majority of innovations happen by a synthesis or recombination of prior innovations, and that inventors and designers, as they gain experience, learn optimal recombination strategies. Our findings provide new insights into the winning strategies of experienced designers in crowdsourcing platforms and have implications for the design of such markets.