Evaluating Fidelity of Explainable Methods for Predictive Process Analytics

Velmurugan, Mythreyi; Ouyang, Chun; Moreira, Catarina; Sindhgatta, Renuka

doi:10.1007/978-3-030-79108-7_8

Cited by 21 publications

(11 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Predictive process monitoring is concerned with the early prediction of the future state of an ongoing case. Predictive efforts are primarily driven by using machine learning models such as XGBoost [3,21,22], random forest [8,23,3], support vector machines [8,3] or logistic regression (LR) [3], with recent works showing interest in applying deep learning models [24,25]. A wide range of works have already evaluated these different models with performance-based metrics [3,8,26].…”

Section: Related Work and Motivationmentioning

confidence: 99%

“…It has already been pointed out that the post-hoc explainability techniques should uncover, apart from an interpretable explanation, the true reasons for model predictions [14,15,36]. Many papers have already investigated the unfaithfulness of post-hoc explainability models [37,21,38,36]. A recent study by Ma [37] has suggested that there was a non-monotonic relationship between the SHAP values and the predictive performance.…”

Section: Related Work and Motivationmentioning

confidence: 99%

“…A recent study by Ma [37] has suggested that there was a non-monotonic relationship between the SHAP values and the predictive performance. Similarly, Velmurugan [21] investigated the faithfulness of SHAP versus LIME based on perturbations, reporting low-to-moderate faithfulness scores. The use of an attention mechanism to interpret the importance of attributes has also been questioned [36,38].…”

Section: Related Work and Motivationmentioning

confidence: 99%

See 2 more Smart Citations

Explainable Predictive Process Monitoring: Evaluation Metrics and Guidelines for Process Outcome Prediction

Stevens¹,

Smedt²

2022

Preprint

View full text Add to dashboard Cite

Recently, a shift has been made in the field of Outcome-Oriented Predictive Process Monitoring (OOPPM) to use models from the eXplainable Artificial Intelligence paradigm, however the evaluation still occurs mainly through performancebased metrics not accounting for the implications and lack of actionability of the explanations. In this paper, we define explainability by the interpretability of the explanations (through the widely-used XAI properties parsimony and functional complexity) and the faithfulness of the explainability model (through monotonicity and level of disagreement). The introduced properties are analysed along the event, case, and control flow perspective that are typical of a process-based analysis. This allows to quantitatively compare, inter alia, inherently created explanations (e.g., logistic regression coefficients) with post-hoc explanations (e.g., Shapley values). Moreover, this paper contributes a guideline named X-MOP to practitioners to select the appropriate model based on the event log specifications and the task at hand, by providing insight into how the varying preprocessing, model complexity and post-hoc explainability techniques typical in OOPPM influence the explainability of the model. To this end, we benchmark seven classifiers on thirteen real-life events logs.

show abstract

Section: Related Work and Motivationmentioning

confidence: 99%

Section: Related Work and Motivationmentioning

confidence: 99%

Section: Related Work and Motivationmentioning

confidence: 99%

See 1 more Smart Citation

Explainable Predictive Process Monitoring: Evaluation Metrics and Guidelines for Process Outcome Prediction

Stevens¹,

Smedt²

2022

Preprint

View full text Add to dashboard Cite

show abstract

“…So there is no consistent way of finding this minimum counterfactual. Although there are some metrics that are used for feature attribution XAI algorithms, such as fidelity [16] and stability [17], there is no standardised way of evaluating XAI algorithms in general, which increases the complexity and difficulty of developing a benchmark evaluation for counterfactuals.…”

Section: The Problem Of Validation Of Counterfactual Explanationsmentioning

confidence: 99%

Benchmark Evaluation of Counterfactual Algorithms for XAI: From a White Box to a Black Box

Chou¹,

Hsieh²,

Moreira³

et al. 2022

Preprint

Self Cite

View full text Add to dashboard Cite

Counterfactual explanations have recently been brought to light as a potentially crucial response to obtaining human-understandable explanations from predictive models in Explainable Artificial Intelligence (XAI). This counterfactual explanation claims to be capable of identifying the smallest feature change capable of changing a prediction. It produces an explanation that is more causally informative than factual explanations in terms of expanding human knowledge of decision making. Despite the fact that various counterfactual algorithms have been proposed, the state of the art research still lacks on standardised protocols to evaluate the quality of counterfactual explanations.In this work, we conducted a benchmark evaluation across different model agnostic counterfactual algorithms in the literature (DiCE, WatcherCF, prototype, unjustifiedCF), and we investigated the counterfactual generation process on different types of machine learning models ranging from a white box (decision tree) to a grey-box (random forest) and a black box (neural network). We evaluated the different counterfactual algorithms using several metrics including proximity, interpretability and functionality for five datasets.The main findings of this work are the following: (1) without guaranteeing plausibility in the counterfactual generation process, one cannot have meaningful evaluation results. This means that all explainable counterfactual algorithms that do not take into consideration plausibility in their internal mechanisms cannot be evaluated with the current state of the art evaluation metrics; (2) the counterfactual generated are not impacted by the different types of machine learning models; (3) DiCE was the only tested algorithm that was able to generate actionable and plausible counterfactuals, because it provides mechanisms to constraint features; (4) WatcherCF and UnjustifiedCF are limited to continuous variables and can not deal with categorical data.

show abstract

“…emerging [4] and several works have been focusing in comparing and evaluating explanations produced by different frameworks [28,29,30,31,32]. The explainable survey of Stierle et al [5] reports on the repertoire of techniques that were developed to address this problem.…”

Section: Explanations In the Bpm Fieldmentioning

confidence: 99%

An Explainable Decision Support System for Predictive Process Analytics

Galanti¹,

Leoni²,

Monaro³

et al. 2022

Preprint

View full text Add to dashboard Cite

Predictive Process Analytics is becoming an essential aid for organizations, providing online operational support of their processes. However, process stakeholders need to be provided with an explanation of the reasons why a given process execution is predicted to behave in a certain way. Otherwise, they will be unlikely to trust the predictive monitoring technology and, hence, adopt it. This paper proposes a predictive analytics framework that is also equipped with explanation capabilities based on the game theory of Shapley Values. The framework has been implemented in the IBM Process Mining suite and commercialized for business users. The framework has been tested on real-life event data to assess the quality of the predictions and the corresponding evaluations. In particular, a user evaluation has been performed in order to understand if the explanations provided by the system were intelligible to process stakeholders.

show abstract

Evaluating Fidelity of Explainable Methods for Predictive Process Analytics

Cited by 21 publications

References 8 publications

Explainable Predictive Process Monitoring: Evaluation Metrics and Guidelines for Process Outcome Prediction

Explainable Predictive Process Monitoring: Evaluation Metrics and Guidelines for Process Outcome Prediction

Benchmark Evaluation of Counterfactual Algorithms for XAI: From a White Box to a Black Box

An Explainable Decision Support System for Predictive Process Analytics

Contact Info

Product

Resources

About