Predicting CEO Misbehavior from Observables: Comparative Evaluation of Two Major Personality Models

Abstract

The primary purpose of this study is to demonstrate how publicly observable pieces of information can be used to build various psychological profiles that can be utilized for the prediction of behavior within a risk analysis framework 1 . In order to evaluate the feasibility of the proposed method, publicly available interview data is processed from a sample of chief executive officers (CEOs) using the IBM Watson Personality Insights service. The hypothesis-that group membership gives rise to a specific selection bias-is investigated by analyzing the IBM Watson-derived personality profiles at the aggregate level. The profiles are represented by two major theories of motivation and personality: the Basic Human Values and the Big Five models. Both theories are evaluated in terms of their utility for predicting adverse behavioral outcomes. The results show that both models are useful for identifying group-level differences between (1) the sample of CEOs and the general population, and (2) between two groups of CEOs, when a history of rule-breaking behavior is considered. The predictive performance evaluation conducted on the current sample shows that the binary logistic regression model built from the Basic Human Values outperforms the Big Five model, and that it provides a practically more useful measurement of individual differences. These results contribute to the development of a risk analysis method within the domain of information security, which addresses human-related risks.

Human Behavior Prediction for Risk Analysis

“…The method relies on the unobtrusive assessment of the strategy owner's relevant utility factors by a risk analyst, which is necessary since strategy owners are assumed to be adversarial (reluctant to interact with an analyst) and may be tempted to subvert the analysis by reporting false information. Previous work used the theory of basic human values (BHV) to operationalize a set of psychologically important utility factors [35], and investigated the extent to which observable features can be used for constructing the motivational profiles of strategy owners [37]. The theory of BHVs [29] distinguishes between 10 motivationally distinct desirable end-goals which form four higher dimensions as shown in Fig.…”

Representing Decision-Makers in SGAM-H: The Smart Grid Architecture Model Extended with the Human Layer

“…KILE (quality-adjusted revenue frames for energy not delivered) represents customers' costs for interruptions, and is a form of revenue reduction due to interruptions, which aims at incentivizing utility companies to maintain operational reliability [29]. Utility factors capturing personal motivations were operationalized in previous work as publicly observable pieces of information, for the construction of motivational profiles [39,41,40]. Table 4 presents how each utility factor is operationalized.…”

“…Table 4 presents how each utility factor is operationalized. Publicly available pieces of information for psychological profiling: text analysis [39], demographic features [41], item ownership and habits [40].…”

“…Weights (w) of the personal utility factors capture the relative importance of basic human values for the subject. Thus, weights are inferred from psychological profiles based on various publicly available pieces of information (e.g., demographics [41], texts produced by the subject [39], evidence of past choices reflecting value trade-offs, habits [40]). Various metrics have been used for quantifying the accuracy/uncertainty of the inferred profiles: R 2 -coefficient of determination (range: 0.19-0.39), PI -prediction interval (Mean: 0.077, SD: 0.794), Pearson correlation coefficients between predicted and ground-truth scores (range: 0.34-0.52) [40].…”