Abstract
This work explores the application of supervised machine learning algorithms on N-body simulations to analyze the membership of open star clusters. The simulations used in this study are based on the Plummer model, clusters formed with constant star-formation efficiency (SFE) per free-fall time. We use simulations with different SFE and initial random realization. The random forest model was trained using simulations based on a 15% SFE over a time period of 20-100 million years. Subsequently, the model was tested on other N-body simulations with SFEs ranging from 17% to 25%, demonstrating consistently high classification accuracy throughout the dynamic evolution of the tested simulations. Most of the errors observed in the model were false positives (FP), often located within a 2 Jacobi radius, suggesting gravitational binding to the cluster's center. This framework and learning strategy exhibit effectiveness and hold promise for further application in analyzing mock observations obtained from N-body simulations.