PBESProceedings of Business and Economic Studies2209-26412209-265XBio-Byword Scientific Publishing Pty. Ltd.10.18063/PBES.v9i8.15156ArticleResearch on the Impact of Digital Inclusive Finance on Urban and Rural Residents’ Income: Causal Effect Analysis Based on the Dual Machine Learning Modelhttps://artdesignp.com/journal/PBES/9/8/10.18063/PBES.v9i8.15156SunYamin2026982026-08-31Narrowing the urban-rural income gap and promoting the sustained growth of urban and rural residents’ income are core issues in advancing common prosperity. Digital inclusive finance, relying on mobile internet and big data credit scoring, provides a new path to overcome the geographical constraints and entry barriers of traditional finance. Based on panel data of prefecture-level cities in China from 2011 to 2024, this paper uses a dual machine learning (DML) partially linear model to identify its causal effect on the per capita disposable income of urban and rural residents. The study found that for every 1-unit increase in the digital inclusive finance index, urban and rural residents’ income increased by approximately RMB 0.274 per person after controlling for the double fixed effects (using the 2011 average as the base period). This conclusion remained robust even after changing the machine learning algorithm, adjusting the cross-fitting split ratio, introducing the time × city and province high-dimensional fixed effects, shortening the sample window, using the city clustering standard error, and adding control variables. Mechanism testing showed that entrepreneurial activity, industrial structure upgrading, and education expenditure levels constituted three significant mediating paths. In terms of heterogeneity, the income-increasing effect was stronger in the eastern, western, and southern regions, as well as in non-old industrial cities, large cities, central cities, and non-resource-based cities, while it was insignificant or weak in the northeast and old industrial cities. Further analysis showed that digital inclusive finance significantly suppressed the Theil index and the urban-rural income ratio. This study provides reusable methods and empirical support for differentiated digital finance policies.Digital inclusive finance, Urban and rural residents’ income, Urban-rural income gap, Dual machine learning, Causal identification

[1] Yang W, Su L, Wang M, 2020, Digital Inclusive Finance and Urban and Rural Residents’ Income: A Mediating Effect Analysis Based on Economic Growth and entrepreneurial behavior. Journal of Shanghai University of Finance and Economics, 22(4): 83–94. [2] Han L, Peng Y, Meng Q, 2023, Digital Inclusive Finance, Entrepreneurial Activity and Common Prosperity: An Empirical Study Based on Inter-Provincial Panel Data in My Country. Soft Science, 37(3): 18–24. [3] Chernozhukov V, Chetverikov D, Demirer M, et al., 2018, Double/Debiased Machine Learning for Treatment and Structural Parameters. The Econometrics Journal, 21(1): 1–68. [4] Zhang B, Li N, 2022, Research on the Impact of Digital Inclusive Finance on the Non-Agricultural Transfer of Rural Labor Force - An Empirical Analysis Based on Mlogit and Threshold Models. World Agriculture, (9): 65–75. [5] Zhao T, Zhang Z, Liang S, 2020, Digital Economy, Entrepreneurial Activity and High-Quality Development: Empirical Evidence from Chinese Cities. Management World, 36(10): 65–76. [6] Jiang T, 2022, Mediating and Moderating Effects in Empirical Studies of Causal Inference. China Industrial Economics, (5): 100–120. [7] Guo F, Wang J, Wang F, et al., 2020, Measuring the Development of Digital Inclusive Finance in China: Index Compilation and Spatial Characteristics. Economics (Quarterly), 19(4): 1401–1418. [8] Yang D, Dai H, Huang F, 2022, A Study on the Threshold Effect of Digital Inclusive Finance on the Income Gap Between Urban and Rural Residents—An Empirical Analysis Based on Different Development Dimensions. Economic and Management Review, 38(3): 89–101.