Unobtrusive Psychological Profiling for Risk Analysis

Adam Szekeres, Einar Arthur Snekkenes

2018

Abstract

The main objective of this exploratory study is to present how publicly observable variables reflecting individual choice can be used to construct psychological profiles suitable for predicting behavior in the context of risk analysis. For the purpose of demonstration, this study aimed at testing the hypothesis that there is a selection bias among chief executive officers (CEOs), which is manifested in their personal value structures. Values capture motivational forces that serve as guiding principles in people’s life when making decisions. From a risk management perspective, it is crucial to understand key decision maker’s motivation in order to be able to prepare against potentially undesirable behavior. Therefore the second objective of this study relates to a detailed characterization of the observed value structures among a group of CEOs. To accomplish these goals a non-obtrusive data collection method is utilized that requires no direct access to individuals - the Watson Personality Insights service provided by IBM - which infers value profiles based on written or spoken text by the subjects. Results show that CEO value profiles differ from the general population in several ways. Furthermore, slight differences were identified between the profiles of CEOs associated with moral hazard and CEOs not associated with it. These findings indicate that there is a meaningful selection bias and these results contribute to the real-world applicability of the CIRA method of risk analysis.

Paper Citation

in Harvard Style

Szekeres A. and Arthur Snekkenes E. (2018). Unobtrusive Psychological Profiling for Risk Analysis.In Proceedings of the 15th International Joint Conference on e-Business and Telecommunications - Volume 1: SECRYPT, ISBN 978-989-758-319-3, pages 210-220. DOI: 10.5220/0006858802100220

in Bibtex Style

@conference{secrypt18,
author={Adam Szekeres and Einar Arthur Snekkenes},
title={Unobtrusive Psychological Profiling for Risk Analysis},
booktitle={Proceedings of the 15th International Joint Conference on e-Business and Telecommunications - Volume 1: SECRYPT,},
year={2018},
pages={210-220},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0006858802100220},
isbn={978-989-758-319-3},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 15th International Joint Conference on e-Business and Telecommunications - Volume 1: SECRYPT,
TI - Unobtrusive Psychological Profiling for Risk Analysis
SN - 978-989-758-319-3
AU - Szekeres A.
AU - Arthur Snekkenes E.
PY - 2018
SP - 210
EP - 220
DO - 10.5220/0006858802100220