• SAMMENGI VIJAY
• Prof. G Suvarna Kumar

Autism Spectrum Disorder (ASD) is a complex neurodevelopmental condition that significantly impacts communication, social interaction, and behavioral patterns. Early-stage detection of ASD plays a crucial role in enabling timely interventions that can improve developmental outcomes and overall quality of life. However, conventional diagnostic methods are often subjective, time-consuming, and dependent on specialized professionals, which creates delays in diagnosis. This research presents a machine learning-based framework for the early detection of ASD using supervised learning algorithms such as Random Forest, Gradient Boosting, and Support Vector Machines (SVM). The framework integrates a robust data preprocessing pipeline that includes feature encoding, missing value imputation, class balancing using SMOTE, feature scaling, and dimensionality reduction with PCA. Both synthetic and real-world ASD screening datasets are utilized to train and validate the models, ensuring accuracy, scalability, and reliability. Model performance is assessed using cross-validation and standard evaluation metrics including accuracy, precision, recall, and F1-score. To enhance real-world usability, the system is deployed on a cloud server with a publicly accessible backend for model inference, while a frontend web application deployed on Vercel enables healthcare professionals and parents to input screening data and receive real-time ASD risk assessments. The dual deployment strategy ensures accessibility, scalability, and cross-platform support. Future enhancements may include integration of deep learning models and multimodal data such as neuroimaging for improved diagnostic precision.

Autism Spectrum Disorder, Machine Learning, Random Forest, Gradient Boosting, Support Vector Machine, SMOTE, PCA, Cloud Deployment

"MACHINE LEARNING FRAMEWORK FOR EARLY-STAGE DETECTION OF AUTISM SPECTRUM DISORDER USING SUPERVISED LEARNING ALGORITHMS", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.12, Issue 9, page no.c673-c681, September-2025, Available :http://www.jetir.org/papers/JETIR2509273.pdf

"MACHINE LEARNING FRAMEWORK FOR EARLY-STAGE DETECTION OF AUTISM SPECTRUM DISORDER USING SUPERVISED LEARNING ALGORITHMS", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.12, Issue 9, page no. ppc673-c681, September-2025, Available at : http://www.jetir.org/papers/JETIR2509273.pdf