Analyzing flight delay prediction under concept drift

Flight delays impose challenges that impact any flight transportation system-predicting when they will occur in a meaningful way to mitigate this issue. However, the distribution of delay system variables changes over time. This phenomenon is known predictive analytics as concept drift. paper investigates prediction performance different drift handling strategies aviation under scales (models trained from flights related single airport or entire system). Specifically, two research questions were proposed and answered: (1) how do influence delays? (2) Do change results strategies? In our analysis, are relevant, their impacts vary according scale machine learning models.