Use of prediction bias in active learning and its application to large variable annuity : Portfolios

Hyukjun Gweon, Shu Li and Yangxuan Xu

Given the computational challenges associated with valuing large variable annuity (VA) portfolios, a variety of data mining frameworks, including metamodeling and active learning, have been proposed in recent years. Active learning, a promising alternative to metamodeling, enhances the efficiency of VA portfolio assessments by adaptively improving a predictive regression model. This is achieved by augmenting data for model training with strategically selected informative samples. Successful application of active learning requires an effective metric in order to gauge the informativeness of data. Current sampling methods, which focus on prediction error-based informativeness, typically rely solely on prediction variance and assume an unbiased predictive model. In this paper, we address the fact that prediction bias can be nonnegligible in large VA portfolio valuation and investigate the impact of prediction bias in both the modeling and sampling stages of active learning. Our experimental results suggest that bias-based sampling can rival the efficacy of traditional ambiguity-based sampling, with its success contingent upon the extent of bias present in the predictive model.

MoreLess

Year of publication:	2024
Authors:	Gweon, Hyukjun ; Li, Shu ; Xu, Yangxuan
Subject:	active learning \| data mining \| machine learning \| prediction bias \| variable annuity \| Prognoseverfahren \| Forecasting model \| Künstliche Intelligenz \| Artificial intelligence \| Data Mining \| Data mining \| Theorie \| Theory \| Lernprozess \| Learning process \| Portfolio-Management \| Portfolio selection \| Systematischer Fehler \| Bias \| Lernen \| Learning

Type of publication:	Article
Type of publication (narrower categories):	Aufsatz in Zeitschrift ; Article in journal
Language:	English
Other identifiers:	10.3390/risks12060085 [DOI]
Source:	ECONIS - Online Catalogue of the ZBW

Persistent link: https://ebvufind01.dmz1.zbw.eu/10014636846