This study aims to address the e-inclusion problem related to digital skills improvement and meaningful use. In professional work, more and more jobs require the use of digital skills. Combining e-learning and face-to-face training is a convenient and affordable way to learn new digital skills. However, the problem is the low number of e-learning graduates and the even lower number of those who use the newly acquired skills for professional or personal purposes. Machine learning approach is used to predict student achievement and other events. However, no comprehensive study has been conducted, analyzing how to improve digital skills training by ensuring that newly acquired skills are meaningfully used in professional life. This paper explores how to predict students’ learning impact outcomes - the use of newly acquired digital skills. We are using classification algorithms and machine learning approaches. We have compared five different classification algorithms and selected the ones with the best performance: LMT and lazy.LWL. We concluded that at least 81.60% of learners identified as not e-included are correctly predicted with lazy.LWL.