A comparison of wavelet networks and genetic programming in the context of temperature derivatives
- Submitting institution
-
The University of Essex
- Unit of assessment
- 11 - Computer Science and Informatics
- Output identifier
- 1437
- Type
- D - Journal article
- DOI
-
10.1016/j.ijforecast.2016.07.002
- Title of journal
- International Journal of Forecasting
- Article number
- -
- First page
- 21
- Volume
- 33
- Issue
- 1
- ISSN
- 0169-2070
- Open access status
- Compliant
- Month of publication
- September
- Year of publication
- 2016
- 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
- 9
- Proposed double-weighted
- No
- Reserve for an output with double weighting
- No
- Additional information
- This paper introduced two novel algorithms: wavelet networks and genetic programming tailored to the dynamics of the daily average temperature in the context of weather derivatives. Experiments were conducted over a large number (180) datasets and subjected to through statistical analysis to ensure rigour. Results indicate that wavelet networks significantly outperform all other state-of-the-art algorithms, both financial and machine learning. This is significant, as the proposed algorithm enables better temperature prediction, which can lead to improved pricing of the derivatives, and thus reduced losses for traders.
- Author contribution statement
- -
- Non-English
- No
- English abstract
- -