Abstract: To improve the prediction accuracy of traffic volume and the utilization rate of transportation construction resources in low traffic demand areas, this study used statistical data from 2011 to 2022 in a specific low traffic demand area to analyze the correlation between economic production and transportation development. Correlation analysis was used to verify the reliability of key indicators, such as GDP, industrial output, and automobile ownership, for calculating the elasticity coefficient calculation. Additionally, grey relational analysis (GRA) was applied to assess the influence of the industrial economic volume and structure on the regional variability of elasticity coefficients. The study identified industrial structure as the crucial factor in dividing regions for elastic coefficient research and used k-means clustering method to categorize the study area into three types of regions. Furthermore, the regression prediction model of the elasticity coefficient over time was developed by dynamic elasticity coefficient calculation methods and logarithmic regression analysis in different areas. Finally, the study validated the models using four low-traffic-volume expressways in the region, comparing actual statistical data with predicted values from 2012 to 2022. Results show that the prediction accuracy of elasticity coefficient and traffic volume reaches 99.06% and 91.09%, respectively. The research provides a more scientific reference basis and more accurate method for the rational forecasting of traffic volume and the optimal resource allocation in low traffic demand areas.