Random forest is an advanced supervised machine learning method to build models for complex systems. This technique belongs to the ensemble method class, one of the most high-powered approaches in artificial intelligence. The flexibility of this technique allows its application to classification and regression tasks. Here, we aim to build a regression model to calculate binding affinity based on docked structures determined with the program Molegro Virtual Docker. A Google Colab workflow permits us to employ the docking results to generate regression models. Our code relies on the Random Forest method available in the Scikit-Learn library. We built a Random Forest model to predict the inhibition of cyclin-dependent kinase 2. This enzyme participates in the control of cell cycle progression and is a target for anticancer drugs. All datasets and Jupyter Notebooks with MVD4ML and SKReg4Model discussed in this work are available at GitHub: https://github.com/azevedolab/docking#readme . We made the program SAnDReS 2.0 available at https://github.com/azevedolab/sandres .