García-Heras Carretero, JavierSánchez Vázquez, Ignacio2020-01-272020-01-272018-092018-09-09https://hdl.handle.net/10016/29552Air traffic in Europe is constantly increasing. Due to this, Air Traffic Management is getting more complex and all stakeholders get affected by that. Among these, air traffic controllers are the ones that suffer the biggest impact in terms of overload of work. Every day, a set of regulations occurs in the regions controlled by these operators, which provokes delays on ground and rerouting in mid-air. All of these variations directly affect the entire ATM network and translates into big expenses for passengers and airlines. With this project, the aim is to predict these daily contingencies by using big data analysis models, so that costs associated are reduced. Most of the information needed to run the analysis has been very complicated to extract, process and correlate because the data sources are not open to researchers. Therefore, the number of instances available for the prediction is very low (only 18 months of data). Nevertheless, while working with this limitation, a Naive Bayes classifier has been chosen as the analytical algorithm. In terms of results, the work done does not reveal a high predictive capability due to the amount of data acquired and the simplicity of the temporal variables. This suggests that, in future researches, it could be convenient to intake broader historical data (more years). Moreover, more complex predictive models could be implemented if variables coming from the weather or the number of flights are used.engAtribución-NoComercial-SinDerivadas 3.0 EspañaAir traffic control (ATC)Big dataAir Traffic Control CentersPython (Programming language)Data Miningbachelor thesisAeronáuticaopen access