For a study, early identification of autism spectrum disorder (ASD) provided an opportunity for early intervention and improved developmental results. Using electroencephalography (EEG) information collected at two different ages during a passive phoneme task in infants with high familial risk for ASD, researchers compared the predictive accuracy of a combination of feature selection and machine learning models at six months (during native phoneme learning) and 12 months (after native phoneme learning). They identified a single model with substantial predictive accuracy (100%) for both ages. The use of EEG in infancy has shown promise in predicting later ASD diagnoses and in identifying neural mechanisms underlying the disorder. Using a combination of Pearson correlation feature selection and support vector machine classifier, 100% predictive diagnostic accuracy was observed at both 6 and 12 months. Predictive features differed between the models trained on 6 versus 12-months data. At 6 months, predictive features were biased to central electrodes, power measures, and frequencies in the alpha range. At 12 months, predictive features were more distributed between power and nonlinear measures and biased toward frequencies in the beta range. However, diagnosis prediction accuracy substantially decreased in the larger, more behaviorally heterogeneous 12-month sample. These results demonstrated that speech processing EEG measures could facilitate earlier identification of ASD but emphasized the need for age-specific predictive models with large sample sizes to develop clinically relevant classification algorithms.