The goal of this thesis is to predict the number of errors and their duration within
a given time frame in information systems, which would help us determine the
performance of the system in the near future. The baseline models are based on
statistical methods such as linear regression and the ARIMA model. We then move
on to more advanced machine learning techniques involving neural networks. Our
analysis shows that we can quite precisely predict the behavior of the system in
the nearby future, which can help us improve the reliability and overall integrity
of the system. The thesis serves as a starting point for further research into the
field of prediction and optimization of information systems.
|
