Biography

s an experienced academic professional in Information Technology with over 15 years of teaching and research experience. He holds a Ph.D. in Data Science and specializes in Big Data Analytics, Cloud Computing, and Business Intelligence. He has published over 30 research articles in international journals and conferences. He has supervised several student projects and actively contributes to interdisciplinary research. He has organized seminars and workshops on cloud technologies and analytics platforms. Dr. Aravind is actively involved in curriculum design and academic planning. He collaborates with industry professionals to bring practical insights into the classroom. He is a member of professional organizations and participates in academic review activities. His research interests include predictive analytics and data visualization. He has received recognition for his contributions to teaching and research. He also contributes to book chapters and technical content development. He is dedicated to developing innovative learning environments and mentoring students for academic and professional success.Weather the flight takeoff or landing management, airline management, air traffic, air traffic control passenger reasons and a host of other factors make it more difficult to pinpoint exactly what causes flight delays these days [3]. Flight security operations and resource scheduling will be further burdened as a consequence of aircraft delays which will upset Keywords—National Airspace System (NAS), Information Gain (IG), Naïve Bayes Classifier (NBC), Bidirectional Long-Shot Term Memory (BiLSTM), Random Forest Classifier (RFC). I. INTRODUCTION The flight delay prediction studies in the past most of those studies have focused on short timeframes like or up to and have mostly been applied to airline services. International flights traverse great distances across seas and continents and their durations range from 10 to 20 hours. This highlights the need for delay prediction over longer timeframes. The capacity to forecast aviation delays over lengthy time periods using input data opens up new possibilities for long-haul flights and different flight itineraries which is a practical use of such models. Flight resource management is only one area that stands to gain from this enhanced capability are many other uses [1]. Uncertainties abound in the aviation industry which is characterized by its dynamism, competitiveness and volatility. These uncertainties include flight delays caused by 979-8-3315-3348-9/25/$31.00 ©2025 IEEE the allocation plans for limited airport resources including runways, aprons and routes and so on. Flight operating, maintenance and human resource expenses may rise due to aircraft delays cutting into profitability. If a passenger's flight is delayed it can ruin their vacation plans or business trip plans. Insurers rely heavily on flight delay prediction data to set premiums and run their flight delay and travel insurance policies. These issues can be ameliorated with the use of this categorization prediction of flight delays. Flight schedules that are likely to experience delays by analyzing huge data using a variety of techniques to avoid these issues [4]. The private airline's enormous data set includes every flight that had place that year. There is flight data and then there is meteorological data for the time period. Flight decision-making processes and ground operations have been examined from numerous angles due to the topic's crucial role in air traffic control. In conducted the initial research [5]. Using weather data collected between domestic flights d