This study explores the use of machine learning models, specifically Classification and Artificial Neural Networks (ANN), to predict the slump and compressive strength of normal and high-early strength concrete. Conducted at a concrete batching plant in Binh Thuan, Vietnam, this research aims to improve quality management and optimize mix designs. The classification model accurately predicts the slump of fresh concrete with an R-squared value of 0.925. Additionally, the Support Vector Machine (SVM) model also effectively distinguishes between normal and high-early strength concrete types. The ANN model shows superior performance in predicting compressive strength, achieving an R-squared value of 0.983. The findings demonstrate the potential of classification and ANN models in the concrete industry, providing engineers with precise tools for adjusting mix proportions. This approach significantly improves the accuracy of predicting concrete performance, ensuring desired quality and durability. The research advances the application of machine learning in civil engineering, promoting more efficient and effective quality management in concrete production.