In engineering geology and geotechnical engineering, it is well recognized that subsurface soils and rocks are natural geomaterials and exhibit inherent spatial variability in stratigraphy. Explicit knowledge of subsurface stratigraphy is a critical input for the analysis, design, and construction of geotechnical systems. However, the accurate and reliable modelling of subsurface geological stratigraphy is challenging due to the limited number of available boreholes in practice and the non-ordered nature of soil stratigraphy. This paper presents an innovative machine learning framework built upon the neighborhood aggregation technique for the prediction of digitized subsurface geological stratigraphy. To predict the stratigraphy at a given point of interest, neighborhood aggregation is first performed to intelligently consolidate the stratigraphy information from its neighboring boreholes, resulting in additional features associated with the target location. By combining the extra stratigraphy information with conventional location-specific features, the framework enhances the predictive capabilities of classical machine learning models at a finer scale. The proposed framework is implemented using two common machine learning models and is cross-validated and evaluated using simulated examples. The results of leave-one-out cross-validation demonstrate that the proposed framework can improve the performance of classical machine learning models, leading to more reasonable stratigraphy interpretation and associated uncertainty quantification. The proposed framework also supports the digitization of both 2D and 3D geological models.