KEY INFLUENCING FACTORS AND TREND PREDICTION OF SHANDONG’S FOREIGN TRADE NEW PRODUCTIVITY DRIVEN BY DIGITAL TRADE
Keywords:
Digital trade, Foreign trade new productivity, Influencing factors, Random forest, Ridge regressionAbstract
Taking the development of foreign trade new productivity driven by digital trade as the main line, this study constructs a multi-dimensional evaluation system based on the panel data of 16 prefecture-level cities in Shandong Province from 2018 to 2023. The entropy weight method is adopted to calculate the comprehensive index of foreign trade new productivity. A random forest model is introduced to identify key influencing factors and quantify their contribution rates. The results show that cross-border e-commerce penetration, digital talent density, and data element circulation efficiency are the core driving factors, with a cumulative contribution rate of 82.3%, highlighting the critical supporting role of digital elements and talents. Furthermore, a ridge regression model is constructed to eliminate multicollinearity. The fitting results are robust with a coefficient of determination of 0.909. The trend prediction indicates that under the current development trend, the comprehensive index of Shandong’s foreign trade new productivity will increase by 19.7% compared with the baseline period, and the regional gap will show a converging trend. The research findings provide quantitative evidence and decision-making reference for formulating differentiated foreign trade upgrading policies and optimizing the digital trade ecosystem.References
[1] Pappaert H, Vandepitte K, Latré J, et al. The Influence of Variety, Nitrogen Level and Sowing Density on the Productivity of Long Fiber Hemp. Journal of Natural Fibers, 2025, 22(1).
[2] Haile D. The effect of agricultural productivity on poverty: what does meta-regression analyses reveal?. Cogent Social Sciences, 2025, 11(1).
[3] Tran TA, Nguyen AP. The Effect of Provincial Governance and Public Administration Performance Index on Total Factor Productivity in Vietnam. Cogent Social Sciences, 2025, 11(1).
[4] Haseeb A, Naz S, Satti S, et al. Comparative impact of selenium sources and doses on sexual behaviour, productivity and gonadal bioaccumulation in Coturnix coturnix japonica. Journal of Applied Animal Research, 2025, 53(1).
[5] Lei Shi, Sheng Gang, Zhao Hao. A Dynamic IPR Framework for Predicting Shale Oil Well Productivity in the Spontaneous Flow Stage. Fluid Dynamics & Materials Processing, 2025, 21(12): 3011-3031.
[6] Li J, Lin S, Hao M. Correction to "Effects of Nitrogen Deposition, Biodiversity and Climate on Productivity in a Large Temperate Forest Region". Global Ecology and Biogeography, 2025, 34(12): e70190.
[7] Bijalwan P, Gupta A, Johri A, et al. The mediating role of workplace incivility on the relationship between organizational culture and employee productivity: a systematic review. Cogent Social Sciences, 2024, 10(1).
[8] Maniriho A. Examining the relationships between ICT-facilitated input market and crop productivity among small-scale farmers in Southern Rwanda. Cogent Social Sciences, 2024, 10(1).
[9] Sisay K. Wellbeing, productivity and food security effects of multiple livelihood diversifications: Insight from kaffa zone, Ethiopia. Cogent Social Sciences, 2024, 10(1).
[10] Yang Wanjun, Wang Chunan. Agricultural land marketization and productivity: evidence from China. Journal of Applied Economics, 2022, 25(1): 22-36.