Understanding Gig Economy Participation: A K-Means Clustering Approach

Abstract

The gig economy reshapes the traditional employment frameworks, providing flexible job opportunities across different industries. Hence, the gig employees encounter various satisfaction levels and challenges depend on their engagement patterns. This study collects real-time data among the gig workers. The 201 respondents are responded to this study. Initially, Exploratory Data Analysis (EDA) is performed to understand the trends within the dataset and discovers the meaningful pattern among the gig workers. EDA assists knowing the insights such as various gig platforms, working hours per week, satisfaction level, and challenges encountered by multiple worker segments. In this study, the K-means Clustering algorithm classifies the gig workers as Active Seekers, Stable Performers, and Low Engaged. These three different cluster separation is based on various key metrics such as work per week, satisfaction level, challenges, and continue-to-work in gig platforms and recommending to another user. The finding shows both Active Seekers and Low Engaged users experiencing huge challenges, due to lack of stable opportunities and workloads. In contrast, Stable Performers tend to have balanced experiences. The study highlights the important inferences for gig platforms, underscoring the necessity health benefits, enhanced worker support and standard policy that encourage sustainable engagement. These findings can help the gig platform to increase the worker retention, improve satisfaction and develop a more resilient gig workspace.