A Study on Supervised Machine Learning-based Airports/Flight Delay Analysis and Classification

Bhawana Pillai; Simran Jot Singh Sodhi

Abstract

Airline delays are a major cause of the financial losses that plague the global aviation business. Airports, airlines, and passengers all suffer when flights are delayed. Their forecast is vital to the commercial aviation industry's decision-making process. Flight presents a significant obstacle for the aviation sector. Increased air traffic and subsequent flight delays are a direct result of the aviation industry's rapid growth over the past two decades. The economic and ecological costs of flight delays are significant. Flight delays can lead to significant financial setbacks for commercial airlines. That is why they take all the precautions they can think of to ensure that flights are not cancelled or delayed. From a data science point of view, this study gives a comprehensive literature analysis of methods for constructing flight delay prediction models. In this article, we take a look at a taxonomy of efforts made to solve the issue of flight delay prediction and characterize them in terms of their scope, data, and computational approaches, paying special emphasis to the growing prevalence of machine learning methods. In addition, the complexity of the air transportation system, the plethora of forecast methodologies, and the flood of flight data made it difficult to construct effective prediction models for flight delays. Predicting flight delays using machine learning techniques is the topic of this article. The focus of this study is on determining whether or not various machine learning techniques can accurately predict flight delays and isolate the most important contributors to such disruptions. Airline schedules, airport wait times, weather forecasts, and other characteristics are all included in the dataset used for the research. The study opens with a summary of prior research on the topic of utilizing machine learning to anticipate aircraft delays. Overall, the results of this study suggest that machine learning approaches may enhance the precision and utility of flight delay forecasts, leading to a safer and more efficient aviation infrastructure.

A Study on Supervised Machine Learning-based Airports/Flight Delay Analysis and Classification

Abstract

Read more of it

Publish your article

Abstract

Related articles

The Role of Artificial Intelligence in Mental Health: New Approaches for Diagnosis and Treatment

AI-Assisted Code Generation: Integrating Natural Language Models with Compiler Frameworks for Enhanced Software Development

A Machine Learning Framework for Fake News Detection Using Embeddings and Dimensionality Reduction

A Secured Check-In and Check-Out System Using Private Key Authentication and QR Code Verification Techniques for Daycare Management

Hybrid Evolutionary Algorithm for Automated Test Case Generation in Large-Scale Software Systems

Read more of it

Publish your article