Extreme Value Scenario Tree Generation Approaches
- DOI
- 10.2991/icemaess-15.2016.155How to use a DOI?
- Keywords
- Scenario; Scenario tree; Extreme value k-means clustering
- Abstract
In actual investment decision activity, investors are usually risk averse and always pay more attention to the tail characteristic of the loss distribution. However, the tail matching effect is not considered in existing scenario tree generation approaches. In light of this phenomenon, a new extreme value k-means clustering method is first presented to generate the scenario tree, and also, by simultaneously utilizing simulation, extreme value k-means clustering, we devise one new multistage scenario tree generation approach. Empirical results show that the better actual performance effect of the new multistage scenario tree generation approach.
- Copyright
- © 2016, the Authors. Published by Atlantis Press.
- Open Access
- This is an open access article distributed under the CC BY-NC license (http://creativecommons.org/licenses/by-nc/4.0/).
Cite this article
TY - CONF AU - Li Yang AU - Weize Wang PY - 2015/12 DA - 2015/12 TI - Extreme Value Scenario Tree Generation Approaches BT - Proceedings of the 2015 3rd International Conference on Education, Management, Arts, Economics and Social Science PB - Atlantis Press SP - 731 EP - 735 SN - 2352-5398 UR - https://doi.org/10.2991/icemaess-15.2016.155 DO - 10.2991/icemaess-15.2016.155 ID - Yang2015/12 ER -