Resource management in SDN (e.g. network slicing) is an emerging area that attracts the attention of academia and industry. It is an indispensable technology in 5G systems. To effectively manage and optimize network resources, more intelligence needs to be deployed. Therefore, combining real network data and Machine Learning (ML) with the benefits of SDN can be a promising solution to manage the network resources in an automated and intelligent way. However, a real network dataset can have redundant and unneeded features. Also, ML algorithms are as good as the quality of data and the SDN is a time-critical system that requires real-time processing and decision. Thus, data preprocessing is a necessary task, which helps to keep the relevant features and makes the prediction quicker and more accurate. This work presents a comparative analysis between two feature selection methods, which are Recursive Feature Elimination (RFE) and Information Gain Attribute Evaluation (InfoGain), using several classifiers on different reduced versions of the network’s dataset.