In the field of construction, the workability of concrete, specifically its ability to flow, is one of the most concerned parameters. In recent times, the integration of artificial intelligence (AI) has brought about a significant transformation in the construction industry, resulting in enhanced efficiency, precision, and innovation. Considering these aspects, the present study has been carried out on a large dataset comprising 1103 data points while taking the ten input parameters into account to predict the flow of concrete. In this regard, six distinct models such as multilayer perceptron (MLP), K-nearest neighbors (KNN), gradient boosting (GB), M5P regression, backpropagation neural networks (BPNN), and lasso regressor have been used to forecast the flow. Along with that, various visualization and evaluation techniques, including scatter plots, histograms, heatmap, coefficient of correlation, errors, SHAP, Taylor’s diagram, have been utilized to illustrate the data availability and performance of models. Based on the output of the study, it has been noticed that the KNN, M5P, and GB models demonstrated exceptional accuracy with negligible errors and high R-squared values (R² ≤ 0.98), whereas other models encountered difficulties in achieving satisfactory performance. This study highlights the significance of water content, coarse aggregates, and fine aggregates as crucial factors that directly affect the flow characteristics of concrete.