Worker Utility as Hysteresis: A Preisach Model of Transaction Acceptance in Gig Labour Markets
Researchers have developed a novel Preisach hysteresis model to better understand worker acceptance in gig labor markets. This model, implemented using a dual-output neural network and an XGBoost classifier, analyzes transaction data to predict worker utility. The system achieved a Jaccard index of 0.827 and an ROC AUC of 0.799 on a dataset of 36,891 gig transactions. The model's findings indicate that price decreases have a more significant negative impact on completion rates than equivalent increases have positive impacts, leading to recommendations that could reduce wage bills by over 21% while increasing fill rates. AI
IMPACT Provides a new framework for optimizing gig economy platforms by modeling worker acceptance and wage dynamics.