In this work, various machine learning techniques, which fall under the category of artificial intelligence, are investigated, and an algorithm (model) is created to forecast the compressive strength of concrete at 7 and 28 days. 180 distinct mixtures with 540 specimens are cast with the intention of building the algorithm (model), and the results are gathered. The information employed in the machine learning model is organized into nine input parameters: cement, fine aggregate, coarse aggregate, water, admixture, compaction factor, w/c ratio, slump, age, and an output parameter: concrete's compressive strength. Concrete's 7- and 28-day compressive strength predictions are based on training and testing outcomes

Compressive strength, Artificial Intelligence, Concrete, Machine learning algorithm, Prediction