Short-term forecasting of non-stationary time series using multiple feature selection methods

Bachelor Thesis (2019)
Author(s)

M.I. Özyar (TU Delft - Electrical Engineering, Mathematics and Computer Science)

Contributor(s)

F.A. Oliehoek – Mentor (TU Delft - Interactive Intelligence)

Miguel Suau de Castro – Graduation committee member (TU Delft - Interactive Intelligence)

Faculty
Electrical Engineering, Mathematics and Computer Science
Copyright
© 2019 Muhammed Imran Özyar
More Info
expand_more
Publication Year
2019
Language
English
Copyright
© 2019 Muhammed Imran Özyar
Graduation Date
28-06-2019
Awarding Institution
Delft University of Technology
Project
CSE3000 Research Project
Programme
Computer Science and Engineering
Faculty
Electrical Engineering, Mathematics and Computer Science
Reuse Rights

Other than for strictly personal use, it is not permitted to download, forward or distribute the text or part of it, without the consent of the author(s) and/or copyright holder(s), unless the work is under an open content license such as Creative Commons.

Abstract

Time series forecasting has been proved to be relatively easier for stationary time series, compared to non-stationary time series. This research proposes a method to partially omit the non-stationarity of the data using prioritized sampling. Using multiple feature selection methods in combination with a random forest regressor (RFR), we aim to predict the values for a non-stationary time series. In particular, the principal component analysis (PCA), kernel PCA, incremental PCA and independent component analysis methods are used. The features extracted from these methods will be fed into an RFR both individually and combined, using the union and intersection operators. The features given by the IPCA ∪ PCA ∪ KPCA method, using prioritized sampling with multiple features per day provide the best improvement over the baseline.

Files

License info not available