This study presents the design and implementation of an innovative educational assistive system tailored for individuals with Autism Spectrum Disorder (ASD), leveraging eye-tracking technology and machine learning algorithms. The objective is to enhance communication and learning experiences through ocular gaze and fixation-based keyboard selection. Data were collected from 15 children with ASD, generating 320 scanpath images that captured fixation duration and gaze direction during left-right and up-down navigation tasks. Using fixation values and Area of Interest (AOI) analysis, a novel keyboard selection method was developed, distinct from traditional digital keyboards. The proposed system was evaluated using an optimized ensemble model, achieving an accuracy of 83.44%, significantly surpassing baseline models. The results demonstrate improved communication efficiency and usability, validating the system’s ability to facilitate hands-free keyboard control. This assistive system fosters better interaction with parents, teachers, and caregivers, promoting social engagement and enhancing the quality of life for individuals with ASD. Overall, this research underscores the transformative potential of integrating eye-tracking and machine learning in educational tools, paving the way for innovative approaches to support neurodiverse learners.