Learning on the Go: Understanding How Gig Economy Workers Learn with Recommendation Algorithms

As gig economy platforms increasingly rely on algorithms to manage on-demand workers, understanding how algorithmic recommendations influence worker behavior is critical for optimizing platform design and improving worker experience. This paper examines the dynamic interactions between gig workers and platform algorithms, focusing on how workers learn to refine their strategies and performance over time. Using multiple quantitative methods, including two-way fixed effects regression and multinomial logit modeling, we analyze more than a million orders completed by gig workers on a retail delivery platform. Our findings reveal a clear learning curve: workers progressively improve their efficiency and on-time delivery performance with experience. Newcomers rely heavily on algorithmic recommendations for task selection, but experienced workers tend to deviate from these recommendations, developing and employing personalized strategies. This shift suggests that experienced workers may perceive algorithmic recommendations as less beneficial or misaligned with their evolved preferences, highlighting the need for adaptive, human-centric systems that evolve with workers' learning trajectories, incorporate their feedback, and offer flexibility to support personalized strategies to enhance collaboration and outcomes for both workers and platforms.