Prevendo o Futuro: Uma Plataforma Web para Modelação de Séries Temporais

Translated title of the contribution: Predicting the Future: A Web Platform for Time Series Modeling

Adriano Leal Vidal, Isabel Sofia Brito, João Paulo Barros, Luis Domingues

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

This article describes a WEB platform for forecasting time series using the ARIMA and SARIMA models. These models are widely used to forecast time series through manual or automatic processes. The platform is designed to analyze meteorological data in time series. It integrates open-source languages and technologies such as Python and the Django framework for data visualization and decision support. As a case study, meteorological data provided by a center that operates in the area of irrigation, were used. Despite the work being in evaluation, the existing preliminary results point to high interest on the part of the members and clients of the center.
Translated title of the contributionPredicting the Future: A Web Platform for Time Series Modeling
Original languagePortuguese
Title of host publication2023 18th Iberian Conference on Information Systems and Technologies (CISTI)
PublisherIEEE Computer Society Press
Number of pages4
ISBN (Electronic)978-989-33-4792-8
ISBN (Print)979-8-3503-0527-2
DOIs
Publication statusPublished - 2023
Event18th Iberian Conference on Information Systems and Technologies, CISTI 2023 - Aveiro, Portugal
Duration: 20 Jun 202323 Jun 2023

Publication series

NameIberian Conference on Information Systems and Technologies (CISTI)
PublisherIEEE Computer Society Press
Volume2023-June
ISSN (Print)2166-0727

Conference

Conference18th Iberian Conference on Information Systems and Technologies, CISTI 2023
Country/TerritoryPortugal
CityAveiro
Period20/06/2323/06/23

Keywords

  • ARIMA
  • decision support
  • forecasting models
  • SARIMA
  • Time Series

Fingerprint

Dive into the research topics of 'Predicting the Future: A Web Platform for Time Series Modeling'. Together they form a unique fingerprint.

Cite this