Sand production is one of the major challenges in the oil and gas industry, impacting the operational integrity and economic efficiency of oil extraction activities. This study focuses on predicting Reservoir Flow Capacity (RFC) in sandstone formations by analyzing geological and petrophysical properties critical to reservoir performance and mechanical stability. It also identified key factors that impact the mechanical stability of formations during production. Given a large number of input variables that enclose geological and environmental factors, the study set the correlation of these conditions to provide profound analysis and reveal profound patterns within the data. With the following supervised machine learning algorithms: Random Forest, Artificial Neural Network (ANN) and Support Vector Regression (SVR); the study modeled RFC. The algorithms were selected for their ability to model complex relationships in reservoir characterization, with Random Forest excelling in high-dimensional data handling, ANN in pattern learning, and SVR in regression-based predictions. Model evaluation using R-Squared metrics showed that the Random Forest model possesses a good level of accuracy of 0.9573 in predicting the RFC, compared to the ANN and SVR model which had R-Squared values of 0.9390 and 0.7294 respectively. The SVR model had large variations from the actual values and hence was not very useful for our predictions. Further analysis using the developed machine learning models revealed that geological formation thickness, reservoir thickness, and permeability are the most critical parameters influencing reservoir flow capacity and overall rock stability.