Decomposition genetic programming: An extensive evaluation on rainfall prediction in the context of weather derivatives
- Submitting institution
-
The University of Essex
- Unit of assessment
- 11 - Computer Science and Informatics
- Output identifier
- 1434
- Type
- D - Journal article
- DOI
-
10.1016/j.asoc.2018.05.016
- Title of journal
- Applied Soft Computing
- Article number
- -
- First page
- 208
- Volume
- 70
- Issue
- -
- ISSN
- 1568-4946
- Open access status
- Compliant
- Month of publication
- May
- Year of publication
- 2018
- URL
-
-
- Supplementary information
-
-
- Request cross-referral to
- -
- Output has been delayed by COVID-19
- No
- COVID-19 affected output statement
- -
- Forensic science
- No
- Criminology
- No
- Interdisciplinary
- No
- Number of additional authors
-
2
- Research group(s)
-
A - Artificial Intelligence (AI)
- Citation count
- 5
- Proposed double-weighted
- No
- Reserve for an output with double weighting
- No
- Additional information
- We present a novel hybrid GP/GA decomposition algorithm for solving regression problems on data with large variability e.g. extremely challenging data like rainfall which is chaotic in nature. 42 datasets are tested, each with 65 years of daily data. Our algorithm significantly outperforms six state-of-the-art ML algorithms yet is general enough for wide application; results were supported by Friedman's statistical test. Significantly, the work deals with the chaotic nature of rainfall data, a real-world problem affecting many businesses, e.g. $1trillion exposed to weather risk in US alone. This is the culmination of several years work on weather derivatives.
- Author contribution statement
- -
- Non-English
- No
- English abstract
- -