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

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 = 6,408). 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.

A Rule Extraction Technique Applied to Ensembles of Neural Networks, Random Forests, and Gradient-Boosted Trees

In machine learning, ensembles of models based on Multi-Layer Perceptrons (MLPs) or decision trees are considered successful models. However, explaining their responses is a complex problem that requires the creation of new methods of interpretation. A natural way to explain the classifications of the models is to transform them into propositional rules. In this work, we focus on random forests and gradient-boosted trees. Specifically, these models are converted into an ensemble of interpretable MLPs from which propositional rules are produced. The rule extraction method presented here allows one to precisely locate the discriminating hyperplanes that constitute the antecedents of the rules. In experiments based on eight classification problems, we compared our rule extraction technique to “Skope-Rules” and other state-of-the-art techniques. Experiments were performed with ten-fold cross-validation trials, with propositional rules that were also generated from ensembles of interpretable MLPs. By evaluating the characteristics of the extracted rules in terms of complexity, fidelity, and accuracy, the results obtained showed that our rule extraction technique is competitive. To the best of our knowledge, this is one of the few works showing a rule extraction technique that has been applied to both ensembles of decision trees and neural networks.

Explainable Neural Network Ensembles

Neural networks are known for providing impressive classification performance, and the ensemble learning technique is further acting as a catalyst to enhance this performance by integrating multiple networks. But like neural networks, neural network ensembles are also considered as a black-box because they cannot explain their decision making process. So, despite having high classification performance, neural networks and their ensembles are not suited for some applications which require explainable decisions. However, the rule extraction technique can overcome this drawback by representing the knowledge learned by a neural network in the guise of interpretable decision rules. A rule extraction algorithm provides neural networks with the power to justify their classification responses through explainable classification rules. Several rule extraction algorithms exist to extract classification rules from neural networks, but only a few of them generates rules using neural network ensembles. So this paper proposes an algorithm named Rule Extraction using Ensemble of Neural Network Ensembles (RE-E-NNES) to demonstrate the high performance of neural network ensembles through rule extraction. RE-E-NNES extracts classification rules by ensembling several neural network ensembles. Results show the efficacy of the proposed RE-E-NNES algorithm compared to different existing rule extraction algorithms.

A Vibrational Signal Fault Diagnosis Rule Extraction Method Based on DST-ACI Discriminant Criterion

A fault diagnosis rule extraction method oriented to machine foot signal based on dynamic support threshold and association coefficient interestingness (DST-ACI) discriminant criterion is proposed in this paper. The new method includes three main innovations. First, the feature state coding method based on K-means clustering fully takes into account the imbalanced distribution of signal feature values due to the noise interference, and divide the signal feature values into several range intervals to generate the feature state code. Second, the frequent feature pattern mining method based on dynamic support threshold (DST) discriminant criterion can dynamically adjust support threshold according to the frequency of the feature states in each candidate pattern. Third, the fault diagnosis rule extraction method based on the association coefficient interestingness (ACI) discriminant criterion introduces a new metrics called ACI to evaluate the correlation between the pattern and the fault. Four types of fault simulation experiments were carried out, and the performance of the DST-ACI method was tested using the collected vibration signal. The results show that compared with the coding method based on equal-width discretization or equal-density discretization, the accuracy of the transactional dataset generated by the feature state coding method based on K-means clustering is higher. Compared with the frequent feature pattern mining method based on the constant support threshold criterion, the pattern mined by the DST-based criterion has generally higher support. Compared with the existing confidence-lift-based and confidence-improint-based fault diagnosis rule extraction frameworks, the positive correlation between the feature states and the fault type of the rules extracted based on the DST-ACI framework is generally stronger.

Rule Extraction From Binary Neural Networks With Convolutional Rules for Model Validation

Classification approaches that allow to extract logical rules such as decision trees are often considered to be more interpretable than neural networks. Also, logical rules are comparatively easy to verify with any possible input. This is an important part in systems that aim to ensure correct operation of a given model. However, for high-dimensional input data such as images, the individual symbols, i.e. pixels, are not easily interpretable. Therefore, rule-based approaches are not typically used for this kind of high-dimensional data. We introduce the concept of first-order convolutional rules, which are logical rules that can be extracted using a convolutional neural network (CNN), and whose complexity depends on the size of the convolutional filter and not on the dimensionality of the input. Our approach is based on rule extraction from binary neural networks with stochastic local search. We show how to extract rules that are not necessarily short, but characteristic of the input, and easy to visualize. Our experiments show that the proposed approach is able to model the functionality of the neural network while at the same time producing interpretable logical rules. Thus, we demonstrate the potential of rule-based approaches for images which allows to combine advantages of neural networks and rule learning.