This study explores how mixing time influences the compressive strength of cement concrete, utilizing machine learning techniques to enhance predictions. Compressive strength is a critical factor in determining the structural integrity and durability of concrete, making it essential for construction applications. Traditional experimental methods to evaluate the effects of mixing time can be time-consuming and may overlook intricate patterns in the data. In this research, machine learning algorithms are employed to predict compressive strength based on various mixing times using the dataset. The study applies regression models and ensemble techniques to capture the complex relationship between mixing time and compression strength accurately. Results indicate that machine learning models are effective in predicting compressive strength of concrete, allowing for the identification of optimal mixing times that enhance performance. This data-driven approach offers a faster, more efficient alternative to traditional experimental methods, streamlining the process of quality control in cement production. Additionally, the findings highlight the potential of machine learning to advance the field of material science by providing deeper insights into optimizing cement properties for better durability and performance in construction projects.