The following files were used for the analyses in the paper “Algorithmic Geology: Tackling Methodological Challenges in Applying Machine Learning to Rock Engineering” (part of the Geosciences special issue on Machine Learning in Engineering Geology) (Yang et al., 2024). The data used in this analysis was synthetic data generated from Rocscience’s SWedge program using a probabilistic Monte Carlo analysis. k-nearest neighbour and multilayer perceptron regression models were developed on varying dataset sizes (ranging from 100 to 4950 with a step of 50), as well as with varying train/test splits and data preparation techniques to investigate the impact of data quantity on machine learning (ML) model results. Surrogate modelling was used, whereby the inputs of the SWedge program are the inputs of the ML models and the output of the SWedge program is the output of the ML models. Additional details can be found in the paper. The “Data” folder contains an Excel file with the synthetic data used to develop the ML models for the paper. The “ML Models” folder contains the ML models examined in the paper. The “ML Results” folder contains the Excel files with the results of each ML model examined in the paper.