File(s) under permanent embargo
Deep neighbor embedding for evaluation of large portfolios of variable annuities
conference contribution
posted on 2019-01-01, 00:00 authored by Xiaojuan Cheng, Wei LuoWei Luo, Guojun Gan, Gang LiGang LiVariable annuities are very profitable financial products that pose unique challenges in risk prediction. Metamodeling techniques are popular due to the significant saving in computation time. However, the current metamodeling techniques still have a low valuation accuracy. One key difficulty is the selection of a small number of contracts that optimally represent the whole portfolio. In this paper, we propose a novel and highly effective method for selecting representative contracts. At the center of this method is a deep neighbor embedding that supports robust clustering of the contracts in a portfolio. The embedding is a low-dimensional representation that respects similarities among contracts in both contract-specific features and their historical performance, achieved through abstract representation in a deep neural network. Empirical results show that the proposed model achieves significant improvement in valuation accuracy, often 10 times or more accurate compared with the popular Kriging-based model.
History
Event
Knowledge Science, Engineering and Management. Conference (2019 : Athens, Greece)Volume
11775Series
Lecture Notes in Computer SciencePagination
472 - 480Publisher
SpringerLocation
Athens, GreecePlace of publication
Berlin, GermanyPublisher DOI
Start date
2019-08-28End date
2019-08-30ISSN
0302-9743ISBN-13
9783030295509Language
engPublication classification
E1 Full written paper - refereedEditor/Contributor(s)
C Douligeris, D Karagiannis, D ApostolouTitle of proceedings
KSEM 2019 : Knowledge Science, Engineering and ManagementUsage metrics
Categories
No categories selectedLicence
Exports
RefWorks
BibTeX
Ref. manager
Endnote
DataCite
NLM
DC