Web Traffic Time Series Forecasting Using LSTM Neural Networks with Distributed Asynchronous Training

Roberto Casado-Vara, Angel Martin del Rey, Daniel Pérez-Palau, Luis de-la-Fuente-Valentín and Juan M. Corchado
Additional contact information
Roberto Casado-Vara: BISITE Research Group, University of Salamanca, 37008 Salamanca, Spain
Angel Martin del Rey: Department of Applied Mathematics, Institute of Fundamental Physics and Mathematics, University of Salamanca, 37008 Salamanca, Spain
Daniel Pérez-Palau: Escuela Superior de Ingeniería y Tecnología, Universidad Internacional de La Rioja, Av. La Paz 137, 26006 Logroño, Spain
Luis de-la-Fuente-Valentín: Escuela Superior de Ingeniería y Tecnología, Universidad Internacional de La Rioja, Av. La Paz 137, 26006 Logroño, Spain
Juan M. Corchado: BISITE Research Group, University of Salamanca, 37008 Salamanca, Spain

Mathematics, 2021, vol. 9, issue 4, 1-21

Abstract: Evaluating web traffic on a web server is highly critical for web service providers since, without a proper demand forecast, customers could have lengthy waiting times and abandon that website. However, this is a challenging task since it requires making reliable predictions based on the arbitrary nature of human behavior. We introduce an architecture that collects source data and in a supervised way performs the forecasting of the time series of the page views. Based on the Wikipedia page views dataset proposed in a competition by Kaggle in 2017, we created an updated version of it for the years 2018–2020. This dataset is processed and the features and hidden patterns in data are obtained for later designing an advanced version of a recurrent neural network called Long Short-Term Memory. This AI model is distributed training, according to the paradigm called data parallelism and using the Downpour training strategy. Predictions made for the seven dominant languages in the dataset are accurate with loss function and measurement error in reasonable ranges. Despite the fact that the analyzed time series have fairly bad patterns of seasonality and trend, the predictions have been quite good, evidencing that an analysis of the hidden patterns and the features extraction before the design of the AI model enhances the model accuracy. In addition, the improvement of the accuracy of the model with the distributed training is remarkable. Since the task of predicting web traffic in as precise quantities as possible requires large datasets, we designed a forecasting system to be accurate despite having limited data in the dataset. We tested the proposed model on the new Wikipedia page views dataset we created and obtained a highly accurate prediction; actually, the mean absolute error of predictions regarding the original one on average is below 30. This represents a significant step forward in the field of time series prediction for web traffic forecasting.

Keywords: web traffic forecast; time series forecast; LSTM; parameter averaging; Downpour strategy; pattern extraction (search for similar items in EconPapers)
JEL-codes: C (search for similar items in EconPapers)
Date: 2021
References: View references in EconPapers View complete reference list from CitEc
Citations:

Downloads: (external link)
https://www.mdpi.com/2227-7390/9/4/421/pdf (application/pdf)
https://www.mdpi.com/2227-7390/9/4/421/ (text/html)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:gam:jmathe:v:9:y:2021:i:4:p:421-:d:503070

Access Statistics for this article

Mathematics is currently edited by Ms. Emma He

More articles in Mathematics from MDPI
Bibliographic data for series maintained by MDPI Indexing Manager ().