Explainable AI for Psychological Profiling from Behavioral Data: An Application to Big Five Personality Predictions from Financial Transaction Records

Abstract

Every step we take in the digital world leaves behind a record of our behavior; a digital footprint. Research has suggested that algorithms can translate these digital footprints into accurate estimates of psychological characteristics, including personality traits, mental health or intelligence. The mechanisms by which AI generates these insights, however, often remain opaque. In this paper, we show how Explainable AI (XAI) can help domain experts and data subjects validate, question, and improve models that classify psychological traits from digital footprints. We elaborate on two popular XAI methods (rule extraction and counterfactual explanations) in the context of Big Five personality predictions (traits and facets) from financial transactions data (N = 6408). First, we demonstrate how global rule extraction sheds light on the spending patterns identified by the model as most predictive for personality, and discuss how these rules can be used to explain, validate, and improve the model. Second, we implement local rule extraction to show that individuals are assigned to personality classes because of their unique financial behavior, and there exists a positive link between the model’s prediction confidence and the number of features that contributed to the prediction. Our experiments highlight the importance of both global and local XAI methods. By better understanding how predictive models work in general as well as how they derive an outcome for a particular person, XAI promotes accountability in a world in which AI impacts the lives of billions of people around the world.

Reinforcement Learning with Intrinsic Affinity for Personalized Prosperity Management

“…In, [14], we gained an understanding of these extracted features by interpreting the dynamics of the RNN state space through a set of attractors. Understanding model behavior is crucial in industries such as personal finance [10]. In their study, [10] extracted rules from three classes of modelslinear regression, logistic regression, and random forests-which not only exposed the spending patterns most indicative of personality traits, but also aided in model improvement.…”

“…Explainability and interpretability are key in sensitive industries, such as finance [9]; they form the basis for understanding and trust and have not yet been adequately addressed [10,11]. In short, our agents' policies are regularized by predefined prior action distributions which imprint characteristic behaviors, making their policies inherently interpretable on three levels: (1) they use salient features extracted from customer spending behavior, (2) the affinity of the prototypical agents, and (3) their orchestration to achieve personal investment advice.…”

Reinforcement learning with intrinsic affinity for personalized prosperity management

“…In Maree and Omlin (2022c), we gained an understanding of these extracted features by interpreting the dynamics of the RNN state space through locating the set of attractors that govern the model. Understanding model behavior is crucial in industries such as personal finance (Ramon et al, 2021). In their study, Ramon et al (2021) extracted rules from three classes of models-linear regression, logistic regression, and random forests-which not only exposed the spending patterns most indicative of personality traits, but also aided in model improvement.…”

“…Understanding model behavior is crucial in industries such as personal finance (Ramon et al, 2021). In their study, Ramon et al (2021) extracted rules from three classes of models-linear regression, logistic regression, and random forests-which not only exposed the spending patterns most indicative of personality traits, but also aided in model improvement.…”

“…Explainability and interpretability form the basis for understanding and trust (Barredo Arrieta et al, 2020). They are imperative for critical industries such as finance, but they have not yet been adequately addressed (Ramon et al, 2021;Cao, 2021). We regularize our agents' policies by predefined prior action distributions, thus imprinting characteristic behaviors that make their policies inherently interpretable on three levels: (1) the salient features extracted from customer spending behavior, (2) the affinities of the prototypical agents, and (3) their orchestration to achieve personal investment advice.…”