Machine Learning-driven Analysis of Determinants Influencing Cooperative Development in Ho Chi Minh City under Digital Transformation

Developing the collective economy with the core of cooperatives is one of the four critical economic sectors in the market economy in Vietnam. The cooperative economic model operates effectively, contributing to sustainable economic development, building new rural areas, creating jobs, eliminating hunger, reducing poverty, and ensuring social security. This study employs advanced methods to identify and quantify the key factors influencing cooperative economic growth in Ho Chi Minh City, as the city undergoes digital transformation and initiatives aimed at making urban areas more sustainable. This study conducted a structured survey with 350 cooperative managers and members. Thereafter, a hybrid analytical framework that combined reliability assessment (Cronbach's Alpha), dimensionality reduction through Exploratory Factor Analysis (EFA), and predictive modelling through multivariate linear regression to process the data was employed. Regularization and model diagnostics were used to make the model stronger and less multicollinear. The adjusted R² value of the optimized regression model (0.676) showed that five meaningful factor clusters had a significant impact on cooperative performance: Policy and Institutional Environment (β = 0.428), Management Capacity – Resources – Technology (β = 0.356), Member Participation (β = 0.306), Market Dynamics (β = 0.274), and Value Chain Integration (β = 0.226). The results show how functional data-driven modelling can be for making specific policy suggestions and actions. The study concludes with practical tactics that use predictive insights to speed up cooperative growth in Ho Chi Minh City's changing digital economy.