Accurate and efficient assessment of rock strength is paramount in the construction industry. Traditional methods for determining properties of rock, such as laboratory testing, are time-consuming and costly, often hindering project timelines and increasing expenses. This research aims to develop an Artificial Neural Network model to predict rock compressive strength based on readily available index properties, including density, void ratio, and water content. By leveraging the capabilities of ANNs, we seek to provide a more rapid and economical alternative to conventional methods. The proposed model was trained and validated using a comprehensive dataset of rock samples. To evaluate the model’s performance, statistical metrics such as Mean Absolute Error, Coefficient of Determination, and Mean Squared Error were employed. Additionally, the influence of rock density on compressive strength was investigated. The successful development of this ANN model holds the potential to significantly improve the efficiency and accuracy of rock strength assessment, ultimately contributing to the optimization of construction projects.