Autism spectrum disorder (ASD) is a neurodevelopmental condition that affects various aspects of individuals' social interactions, communication, learning, and behavior. While ASD can manifest at any stage of life, symptoms typically emerge within the initial two years. Timely identification of autism can greatly influence the effectiveness of its intervention and treatment. This study centers on identifying distinct characteristics that facilitate the automation of the ASD diagnostic process. Additionally, it aims to assess and conduct a comparative examination of different machine learning algorithms such as Decision Tree (DT), K-Nearest Neighbors (KNN), Gaussian Naive Bayes (GNB), Logistic Regression (LR), Gradient Boosting (GB), Artificial Neural Networks (ANN), an Ensemble Model (EM), Support Vector Machine (SVM), Convolutional Neural Network (CNN), and Random Forest (RF) in order to forecast the likelihood of autism disorder. Most importantly four different behavioral datasets following Autism-Spectrum Quotient (AQ-10) screening tool are normalized and merged which consisting of 3492 records, facilitates the development of robust machine learning models to predict the likelihood of ASD. Different performance metrics like; accuracy, precision, recall, F1-score, Specificity and ROC-AUC are employed to make a better comparison of the mentioned algorithms.