International Journal of Scientific Research and Engineering Development

Autism Spectrum Disorder (ASD) is a neurodevelopmental condition that affects communication, social interaction, and behavioral patterns. Early identification of ASD is essential for effective intervention and improved developmental outcomes. This research presents a Python-based machine learning framework for autism prediction using questionnaire-based behavioral and demographic datasets. The proposed system performs data preprocessing, missing value handling, categorical feature encoding, and class balancing using the Synthetic Minority Oversampling Technique (SMOTE). Multiple supervised machine learning algorithms, including Decision Tree, Random Forest, Support Vector Machine (SVM), K-Nearest Neighbors (KNN), and XGBoost, are implemented and compared for classification performance. Hyperparameter optimization using RandomizedSearchCV and cross-validation techniques is employed to improve predictive accuracy and reduce overfitting. Experimental analysis demonstrates that ensemble learning methods, particularly Random Forest and XGBoost, achieve superior classification performance in autism screening tasks. The developed framework provides a scalable, reproducible, and efficient solution for intelligent healthcare analytics and may assist clinicians and researchers in early autism detection and decision-support systems.

Ayan Chakraborty, Mahuya Sasmal,"Autism Prediction Using Machine Learning" International Journal of Scientific Research and Engineering Development, V9(3): Page(970-975) May-June 2026. ISSN: 2581-7175. www.ijsred.com. Published by Scientific and Academic Research Publishing.