Public Data Openness and Urban–Rural Integration—Causal Inference Based on Double Machine Learning

Public data is a foundational resource and new production factor in the digital economy era. Scientific assessment of its economic effects on urban–rural integration is of great significance for promoting the revitalization of rural areas and achieving common prosperity. This study employs a double machine learning (DML) model for causal inference, using the establishment of “data trading platforms” as an exogenous policy shock to measure public data openness (Opendata). The level of urban–rural integration (Uri) is assessed through a comprehensive index system encompassing economic, population, social, spatial, and ecological dimensions, with weights assigned using the CRITIC method. Based on panel data from 259 prefecture-level cities in China (2012–2024), the analysis is conducted using machine learning algorithms such as Lasso regression, supplemented by a series of robustness and endogeneity tests. Research has found that public data openness can significantly promote urban–rural integration, and this conclusion still holds true after a series of robustness tests. Mechanism analysis indicates that public data openness promotes urban–rural integration by facilitating the flow of factors between urban and rural areas and enhancing technological innovation. Heterogeneity analysis shows that the enhancing effect of public data openness on urban–rural integration is more significant in eastern cities and non-resource-based cities. Based on these conclusions, it is recommended to further accelerate the cultivation of a standardized and unified data element market and enrich the “digital soil”, solve the problems of unsmooth flows of factors and resource constraints, strengthen data empowerment in urban–rural information sharing, and promote common prosperity in urban and rural areas.