Flight Delay Prediction Using Machine Learning Algorithms

EasyChair Preprint 15758

Abstract

In today’s time, Flight delays present a significant challenge to the aviation industry, impacting both airline operations and passenger satisfaction. To tackle these problems,this project aims to develop a flight delay prediction mechanism using advanced machine learning models such as Decision Tree Classifier, Random Forest Classifier and XGBoost Classifier.By analyzing a diverse set of features, including historical flight data, weather conditions and other relevant variables, we strive to accurately predict the likelihood of delays. The models’performance is evaluated based on accuracy, precision, and recall score with comparative analysis of each algorithm’s effectiveness.Decision Tree algorithm offers simplicity and interpretability,Random Forest uses concept of ensemble learning hence provides a robust approach to solve the ML tasks whereas XGBoost excels on these tasks with its boosting capabilities and performance on large datasets. The objective of this project is to identify the most effective algorithm for delay prediction and to deliver actionable insights for airlines to enhance scheduling, resource management, and operational efficiency. The ultimate goal of this project is to improve the customer satisfaction for airlines and reduce the financial impact of the problem. The real-life application of this model can lead to more informed decision-making processes and improved passenger experiences.

Keyphrases: Decision Tree Classifier, Random Forest Classifier, XGBoost ., ensemble learning, machine learning

@booklet{EasyChair:15758,
  author    = {Abhishek Kumar Singh and Ujjwal and Sayan Sarkar},
  title     = {Flight Delay Prediction Using Machine Learning Algorithms},
  howpublished = {EasyChair Preprint 15758},
  year      = {EasyChair, 2025}}