The document discusses the development of a genetic algorithm-based neural network model to predict the strength properties of steel fiber reinforced concrete (SFRC) using various input parameters such as water-cement ratio, aggregate-cement ratio, fiber percentage, and fiber aspect ratio. The model demonstrated a 95% accuracy in predicting compressive, flexural, and split tensile strengths after being trained on 108 experimental data sets. The paper emphasizes the advantages of combining artificial neural networks and genetic algorithms to effectively map the complex interactions among the various factors affecting SFRC properties.