Introduction of seasonality concept in PSF algorithm to improve univariate time series predictions
- Published
- Accepted
- Subject Areas
- Artificial Intelligence, Data Mining and Machine Learning, Data Science
- Keywords
- prediction, time series, ARIMA, Seasonality, PSF, R Packages
- Copyright
- © 2016 Bokde et al.
- Licence
- This is an open access article distributed under the terms of the Creative Commons Attribution License, which permits unrestricted use, distribution, reproduction and adaptation in any medium and for any purpose provided that it is properly attributed. For attribution, the original author(s), title, publication source (PeerJ Preprints) and either DOI or URL of the article must be cited.
- Cite this article
- 2016. Introduction of seasonality concept in PSF algorithm to improve univariate time series predictions. PeerJ Preprints 4:e2184v2 https://doi.org/10.7287/peerj.preprints.2184v2
Abstract
This paper proposed a novel modification in Pattern Sequence based Forecasting (PSF) algorithm, named as Seasonal PSF. The proposed modification in PSF algorithm is done with addition of seasonality concept, such that the longer univariate time series database with combination of many sequence patterns and outliers can be converted into more relevant database in accordance with data under test of predictions. In this paper, seasonal PSF is examined on electricity load database for two years, provided by EUNITE network. The comparative analysis consists of two methodologies, multiple steps prediction and one step ahead forecasting. This analysis conclude that, seasonality based decomposition of database leads to much better performance of seasonal PSF over original PSF and benchmarked methods for univariate predictions like ARIMA and SARIMA. It is found that the maximum accuracy is achieved in minimum computational delay with Seasonal PSF. These comparisons are performed with RMSE, MAE and MAPE as error performance metrics.
Author Comment
The manuscript is updated with few grammatical corrections and references.