Aggregate selection, individual selection, and cluster selection: an empirical evaluation and implications for systems research
Vangumalli, D.; Nikolopoulos, K.; Litsiou, K.
Professor Kostas Nikolopoulos email@example.com
Data analysts when forecasting large number of time series, they regularly employ one of the following methodological approaches: either select a single forecasting method for the entire dataset (aggregate selection), or use the best forecasting method for each time series (individual selection). There is evidence in the predictive analytics literature that the former is more robust than the latter, as in individual selection you tend to overfit models to the data. A third approach is to first identify homogeneous clusters within the dataset, and then select a single forecasting method for each cluster (cluster selection). To that end, we examine three machine learning clustering methods: k-medoids, k-NN and random forests. The evaluation is performed in the 645 yearly series of the M3 competition. The empirical evidence suggests: (a) random forests provide the best clusters for the sequential forecasting task, and (b) cluster selection has the potential to outperform aggregate selection.
Vangumalli, D., Nikolopoulos, K., & Litsiou, K. (2021). Aggregate selection, individual selection, and cluster selection: an empirical evaluation and implications for systems research. Cybernetics and Systems, 52(7), 553-578. https://doi.org/10.1080/01969722.2021.1902049
|Journal Article Type||Article|
|Acceptance Date||Mar 8, 2021|
|Online Publication Date||Jun 14, 2021|
|Deposit Date||Mar 9, 2021|
|Publicly Available Date||Jun 14, 2022|
|Journal||Cybernetics and Systems|
|Publisher||Taylor and Francis Group|
|Peer Reviewed||Peer Reviewed|
Accepted Journal Article
Publisher Licence URL
This is an Accepted Manuscript version of the following article, accepted for publication in Cybernetics & Systems. Vangumalli, D., Nikolopoulos, K. & Litsiou, K. (2021). Aggregate selection, individual selection, and cluster selection: an empirical evaluation and implications for systems research. Cybernetics & Systems: An International Journal 52(7): 553-578.. It is deposited under the terms of the Creative Commons Attribution-NonCommercial License (http://creativecommons.org/licenses/by-nc/4.0/), which permits non-commercial re-use, distribution, and reproduction in any medium, provided the original work is properly cited.
You might also like
EXPANDING THE CONCEPT OF ENVIRONMENTAL INTELLIGENCE VIA INNOVATIVE TECHNOLOGIES FOR IN SITU RADIOACTIVITY MONITORING
Presentation / Conference
Forecasting: theory and practice
Radioactivity Monitoring in Ocean Ecosystems (RAMONES).
Monitoring in Ocean Ecosystems Event