Autism Spectrum disorder is one of the neurodevelopmental disorder which consist of a characteristics like poor eye contact, repetitive behavior, harming others and so on. This affects an individual’s life if it is unidentified and untreated with therapies. It can be assessed and identified using some scale like Indian Scale for Assessment of Autism, Modified Checklist for Autism in Toddlers, Autism Behaviour Checklist. It cannot be cured but if it is identified in an early stage and treated with some therapies the particular individual can lead a normal life. In modern era, Artificial Intelligence plays a vital role in predicting Autism Spectrum Disorder by using classification techniques like Naïve Bayes, Decision Tree, Logistic Regression, Random Forest, Support Vector Machine and so on. The main objective of this research is to suggest the best Artificial Intelligence technique for predicting Autism Spectrum Disorder in an early stage so that the individual can be treated with suitable therapies.