Volume 2 - Issue 3, May - June 2026

Flight delays represent a significant challenge in the aviation industry, causing substantial financial losses for airlines and inconvenience for passengers. This paper presents a machine learning-based flight delay prediction system that analyzes historical flight data to classify flights as delayed or on-time. We implement and compare multiple classification algorithms including Random Forest, Logistic Regression, and Naive Bayes using a dataset containing flight records with features such as departure time, airline carrier, origin, destination, and distance. The Random Forest classifier achieved the highest accuracy of 87.3% on the test set. The trained model is deployed through a Flask-based web application, enabling real-time predictions. Experimental results demonstrate that ensemble methods outperform traditional classifiers for this prediction task, and proper feature engineering significantly improves model performance.

Mrs S.Vanitha, Dr.N.Purushothaman, Mrs K Karthika,"A Data-Driven Approach to Flight Delay Prediction Using Machine Learned Classifiers with Error Analysis in Airport Apron Networks" International Journal of Advanced Multidisciplinary Research and Educational Development, V2(3): Page(922-927) May-June 2026. ISSN: 3107-6513. www.ijamred.com. Published by Scientific and Academic Research Publishing.