Time series prediction of web traffic data
(2021) STAN40 20201Department of Statistics
- Abstract
- In this thesis we predict web traffic intensity levels for 7 customers of a cybersecurity company.
The models we predict with are a SARIMA model and a Temporal convolutional network.
The quality of the predictions vary a lot between the different customers.
The predictions improve when performed on data that is logged, demeaned and differenced.
Please use this url to cite or link to this publication:
http://lup.lub.lu.se/student-papers/record/9057479
- author
- Dominguez Berndtsson, Nils LU
- supervisor
- organization
- course
- STAN40 20201
- year
- 2021
- type
- H1 - Master's Degree (One Year)
- subject
- keywords
- Time series predictions, Temporal Convolutional Network, SARIMA, Web traffic, Cybersecurity
- language
- English
- id
- 9057479
- date added to LUP
- 2021-12-14 11:12:33
- date last changed
- 2021-12-14 11:12:33
@misc{9057479, abstract = {{In this thesis we predict web traffic intensity levels for 7 customers of a cybersecurity company. The models we predict with are a SARIMA model and a Temporal convolutional network. The quality of the predictions vary a lot between the different customers. The predictions improve when performed on data that is logged, demeaned and differenced.}}, author = {{Dominguez Berndtsson, Nils}}, language = {{eng}}, note = {{Student Paper}}, title = {{Time series prediction of web traffic data}}, year = {{2021}}, }