Economic Conditions and the Gig Economy: Measuring the Impact and Implications for Social Welfare Programs

Olivia Tirso

 Co-Presenters: Olivia Tirso, Ben Abraham
College: Dorothy and George Hennings College of Science, Mathematics and Technology
Major: Computer Information Systems (M.S.)
Faculty Research Mentor: Ngoc Dao
 

Abstract:

The gig economy has significantly reshaped traditional labor markets, offering workers increased flexibility while simultaneously raising concerns about job security, income stability, and social welfare eligibility. This study synthesizes existing literature on gig work, policy responses, and social security implications while integrating machine learning models to analyze and predict gig economy participation and income levels. Research indicates that gig workers, often classified as independent contractors, face limited access to labor protections and government benefits, leading to financial instability and inconsistent welfare program participation. Policy interventions, such as California’s AB-5 law and the European Union’s Platform Work Directive, aim to redefine employment classifications and extend social protections, yet challenges persist in balancing flexibility with worker security.To further investigate these dynamics, this study applies machine learning techniques, including Random Forest, XGBoost, and Neural Networks, to predict gig economy participation and income variability using Current Population Survey (CPS) and Survey of Household Economics and Decision Making (SHED) data. Results demonstrate that Random Forest (95.05%) and XGBoost (94.97%) outperform traditional models in classification tasks, accurately predicting gig economy engagement based on socioeconomic variables. In income prediction, XGBoost achieves the lowest mean squared error (MSE = 0.0411) and highest R2 (0.3692), highlighting non-linear relationships in gig worker earnings. These findings underscore the potential of AI-driven labor market forecasting and support ongoing policy discussions on enhancing gig worker protections.