ABSTRACT
A surge in global demand for concrete has necessitated the development of innovative concrete variants. Researchers have worked on predicting the strength of concrete using robust models, which can lead to advancements in the present standard. Standard models that have been widely used in statistical and empirical studies are not time efficient to develop and haven’t been consistently good performing in complex scenarios. As an alternative, machine learning models such as decision trees, support vector machines, and artificial neural networks have been explored to address the limitations of standard models. In this study, the applications of each model are critically examined, and their performance is analyzed. This analysis helps identify existing knowledge gaps, offers practical recommendations, and suggests avenues for further research.
