A data-driven analysis to predict energetic intelligence Baca Ruiz, Luis Gonzaga Criado-Ramón, David Serrano-Fernánez, María José Pérez-Moreiras, Elena Pegalajar Jiménez, María Del Carmen machine learning data mining energetic intelligence psychology Energetic Intelligence is a newly defined construct recently validated that offers a thorough understanding of human intelligence by integrating, emotional, spiritual, and physical dimensions. This study applies a data-driven approach to predict Energetic Intelligence. Our research goal lies in the application ofmachine learning techniques to model and predict Energetic Intelligence using data commonly gathered in organizational contexts. We collected responses through structured surveys and employed a range of supervised learning algorithms to build predictive models. Model performance was evaluated using standard metrics, with the best results reaching an R2 of 0.73 through optimized and simplified models, which is a promising outcome for a psychologically grounded prediction task. Key predictors included variables such as Flow, Flourishing, and Emotional Vitality, which consistently emerged as relevant features in model training. These findings demonstrate the potential of machine learning to support psychological research and offer practical tools for the assessment and development of Energetic Intelligence in applied settings. Our work points out the value of integrating AI methodologies with psychological theory to enable data-driven insights into human potential and well-being. 2026-01-26T11:28:33Z 2026-01-26T11:28:33Z 2026-01-23 journal article https://hdl.handle.net/10481/110268 10.1007/s41060-026-01026-8 eng http://creativecommons.org/licenses/by-nc-nd/3.0/ open access Creative Commons Attribution-NonCommercial-NoDerivs 3.0 License Springer Nature