Hypnosis, a state of focused attention and heightened suggestibility, can be used as a therapeutic tool that yields similar effects to those of medications but without known side effects. Despite extensive fascination and study, the neural mechanisms behind hypnosis remain elusive. In the current study, we undertook a systematic exploration of these neural correlates. We first extracted well-studied neurophysiological features from EEG sensors and source-localized data using spectral analysis and two measures of functional connectivity—weighted phase lag index (wPLI) and power envelope correlation (PEC). Next, we developed classification models that predicted self-rated hypnotic experience based on the extracted feature sets. Our findings reveal that gamma power computed on sensor-level data and beta PEC computed between source-localized brain networks are the top predictors of hypnosis depth. Further SHapley Additive exPlanations (SHAP) analysis suggested reduced gamma power in the midline frontal area and increased beta PEC between interhemispheric Dorsal Attention Networks (DAN) contribute to the hypnotic experience. These results broaden our understanding of the neural mechanisms of hypnosis, highlighting potential targets for future research. Moreover, this study demonstrates the potential of using machine learning techniques in understanding the neural underpinnings of hypnosis, offering a template for future investigations. his study was registered at https://doi.org/10.17605/OSF.IO/WVHDA on 30/03/2021.