NORMA eResearch @NCI Library

Comparing Machine Learning Models for Predicting the Global Internet Usage

Sebastian, Tijo (2023) Comparing Machine Learning Models for Predicting the Global Internet Usage. Masters thesis, Dublin, National College of Ireland.

[thumbnail of Master of Science]
PDF (Master of Science)
Download (1MB) | Preview
[thumbnail of Configuration manual]
PDF (Configuration manual)
Download (1MB) | Preview


The internet is increasingly important today. Because every aspect of life is in some manner closely tied to the internet, it is impossible for us to think about a tomorrow without it. The goal of this forecast is to predict network usage using past observations. The internet usage forecast can be beneficial for multiple reasons. The internet service providers are more benefited from this research so that they can plan for their future and implement necessary steps wherever required. The Long Short-term Memory (LSTM) model and the Simple Exponential Smoothing (SES) model are implemented in this research. Both LSTM and SES models are widely used for time series forecasts. The required data is gathered from an open-source platform. The analysis confirmed that the SES model outperformed the LSTM model in accuracy. The model accuracy is measured with appropriate metrics.

Item Type: Thesis (Masters)
Rifai, Hicham
Subjects: Q Science > QA Mathematics > Electronic computers. Computer science
T Technology > T Technology (General) > Information Technology > Electronic computers. Computer science
Q Science > Q Science (General) > Self-organizing systems. Conscious automata > Machine learning
Z Bibliography. Library Science. Information Resources > ZA Information resources > ZA4150 Computer Network Resources > The Internet
T Technology > TK Electrical engineering. Electronics. Nuclear engineering > Telecommunications > The Internet
Divisions: School of Computing > Master of Science in Data Analytics
Depositing User: Tamara Malone
Date Deposited: 25 May 2023 16:25
Last Modified: 25 May 2023 16:25

Actions (login required)

View Item View Item