Mustafa Çavuş

Adrian Stando, Mustafa Cavus, Przemysław Biecek

Imbalanced data poses a significant challenge in classification as model performance is affected by insufficient learning from minority classes. Balancing methods are often used to address this problem. However, such techniques can lead to problems such as overfitting or loss of information. This study addresses a more challenging aspect of balancing methods - their impact on model behavior. To capture these changes, Explainable Artificial Intelligence tools are used to compare models trained on datasets before and after balancing. In addition to the variable importance method, this study uses the partial dependence profile and accumulated local effects techniques. Real and simulated datasets are tested, and an open-source Python package edgaro is developed to facilitate this analysis. The results obtained show significant changes in model behavior due to balancing methods, which can lead to biased models toward a balanced distribution. These findings confirm that balancing analysis should go beyond model performance comparisons to achieve higher reliability of machine learning models. Therefore, we propose a new method performance gain plot for informed data balancing strategy to make an optimal selection of balancing method by analyzing the measure of change in model behavior versus performance gain.

Mustafa Cavus, Adrian Stando, Przemyslaw Biecek

The expected goal models have gained popularity, but their interpretability is often limited, especially when trained using black-box methods. Explainable artificial intelligence tools have emerged to enhance model transparency and extract descriptive knowledge for a single observation or for all observations. However, explaining black-box models for a specific group of observations may be more useful in some domains. This paper introduces the glocal explanations (between local and global levels) of the expected goal models to enable performance analysis at the team and player levels by proposing the use of aggregated versions of the SHAP values and partial dependence profiles. This allows knowledge to be extracted from the expected goal model for a player or team rather than just a single shot. In addition, we conducted real-data applications to illustrate the usefulness of aggregated SHAP and aggregated profiles. The paper concludes with remarks on the potential of these explanations for performance analysis in soccer analytics.

Mustafa Cavus, Jakub Kuzilek

In the past decade, we have experienced a massive boom in the usage of digital solutions in higher education. Due to this boom, large amounts of data have enabled advanced data analysis methods to support learners and examine learning processes. One of the dominant research directions in learning analytics is predictive modeling of learners' success using various machine learning methods. To build learners' and teachers' trust in such methods and systems, exploring the methods and methodologies that enable relevant stakeholders to deeply understand the underlying machine-learning models is necessary. In this context, counterfactual explanations from explainable machine learning tools are promising. Several counterfactual generation methods hold much promise, but the features must be actionable and causal to be effective. Thus, obtaining which counterfactual generation method suits the student success prediction models in terms of desiderata, stability, and robustness is essential. Although a few studies have been published in recent years on the use of counterfactual explanations in educational sciences, they have yet to discuss which counterfactual generation method is more suitable for this problem. This paper analyzed the effectiveness of commonly used counterfactual generation methods, such as WhatIf Counterfactual Explanations, Multi-Objective Counterfactual Explanations, and Nearest Instance Counterfactual Explanations after balancing. This contribution presents a case study using the Open University Learning Analytics dataset to demonstrate the practical usefulness of counterfactual explanations. The results illustrate the method's effectiveness and describe concrete steps that could be taken to alter the model's prediction.

Seyma Gunonu, Gizem Altun, Mustafa Cavus

The accuracy and understandability of bank failure prediction models are crucial. While interpretable models like logistic regression are favored for their explainability, complex models such as random forest, support vector machines, and deep learning offer higher predictive performance but lower explainability. These models, known as black boxes, make it difficult to derive actionable insights. To address this challenge, using counterfactual explanations is suggested. These explanations demonstrate how changes in input variables can alter the model output and suggest ways to mitigate bank failure risk. The key challenge lies in selecting the most effective method for generating useful counterfactuals, which should demonstrate validity, proximity, sparsity, and plausibility. The paper evaluates several counterfactual generation methods: WhatIf, Multi Objective, and Nearest Instance Counterfactual Explanation, and also explores resampling methods like undersampling, oversampling, SMOTE, and the cost sensitive approach to address data imbalance in bank failure prediction in the US. The results indicate that the Nearest Instance Counterfactual Explanation method yields higher quality counterfactual explanations, mainly using the cost sensitive approach. Overall, the Multi Objective Counterfactual and Nearest Instance Counterfactual Explanation methods outperform others regarding validity, proximity, and sparsity metrics, with the cost sensitive approach providing the most desirable counterfactual explanations. These findings highlight the variability in the performance of counterfactual generation methods across different balancing strategies and machine learning models, offering valuable strategies to enhance the utility of black box bank failure prediction models.

Mustafa Cavus, Przemysław Biecek

Predictive models may generate biased predictions when classifying imbalanced datasets. This happens when the model favors the majority class, leading to low performance in accurately predicting the minority class. To address this issue, balancing or resampling methods are critical data-centric AI approaches in the modeling process to improve prediction performance. However, there have been debates and questions about the functionality of these methods in recent years. In particular, many candidate models may exhibit very similar predictive performance, called the Rashomon effect, in model selection, and they may even produce different predictions for the same observations. Selecting one of these models without considering the predictive multiplicity -- which is the case of yielding conflicting models' predictions for any sample -- can result in blind selection. In this paper, the impact of balancing methods on predictive multiplicity is examined using the Rashomon effect. It is crucial because the blind model selection in data-centric AI is risky from a set of approximately equally accurate models. This may lead to severe problems in model selection, validation, and explanation. To tackle this matter, we conducted real dataset experiments to observe the impact of balancing methods on predictive multiplicity through the Rashomon effect by using a newly proposed metric obscurity in addition to the existing ones: ambiguity and discrepancy. Our findings showed that balancing methods inflate the predictive multiplicity and yield varying results. To monitor the trade-off between the prediction performance and predictive multiplicity for conducting the modeling process responsibly, we proposed using the extended version of the performance-gain plot when balancing the training data.

Mustafa Cavus

As machine learning models are increasingly deployed in high-stakes environments, ensuring both probabilistic reliability and prediction stability has become critical. This paper examines the interplay between classification calibration and predictive multiplicity - the phenomenon in which multiple near-optimal models within the Rashomon set yield conflicting credit outcomes for the same applicant. Using nine diverse credit risk benchmark datasets, we investigate whether predictive multiplicity concentrates in regions of low predictive confidence and how post-hoc calibration can mitigate algorithmic arbitrariness. Our empirical analysis reveals that minority class observations bear a disproportionate multiplicity burden, as confirmed by significant disparities in predictive multiplicity and prediction confidence. Furthermore, our empirical comparisons indicate that applying post-hoc calibration methods - specifically Platt Scaling, Isotonic Regression, and Temperature Scaling - is associated with lower obscurity across the Rashomon set. Among the tested techniques, Platt Scaling and Isotonic Regression provide the most robust reduction in predictive multiplicity. These findings suggest that calibration can function as a consensus-enforcing layer and may support procedural fairness by mitigating predictive multiplicity.

Jakub Kuzilek, Mustafa Çavuş

This study explores how the Rashomon effect influences variable importance in the context of student demographics used for academic outcomes prediction. Our research follows the way machine learning algorithms are employed in Educational Data Mining, focusing on highlighting the so-called Rashomon effect. The study uses the Rashomon set of simple-yet-accurate models trained using decision trees, random forests, light GBM, and XGBoost algorithms with the Open University Learning Analytics Dataset. We found that the Rashomon set improves the predictive accuracy by 2-6%. Variable importance analysis revealed more consistent and reliable results for binary classification than multiclass classification, highlighting the complexity of predicting multiple outcomes. Key demographic variables imd_band and highest_education were identified as vital, but their importance varied across courses, especially in course DDD. These findings underscore the importance of model choice and the need for caution in generalizing results, as different models can lead to different variable importance rankings. The codes for reproducing the experiments are available in the repository: https://anonymous.4open.science/r/JEDM_paper-DE9D.

Mustafa Cavus

Many machine learning tasks admit multiple models that perform almost equally well, a phenomenon known as predictive multiplicity. A fundamental source of this multiplicity is observational multiplicity, which arises from the stochastic nature of label collection: observed training labels represent only a single realization of the underlying ground-truth probabilities. While theoretical frameworks for observational multiplicity have been established for logistic regression, their implications for non-smooth, partition-based models like decision trees remain underexplored. In this paper, we introduce two complementary notions of observational multiplicity for decision tree classifiers: leaf regret and structural regret. Leaf regret quantifies the intrinsic variability of predictions within a fixed leaf due to finite-sample noise, while structural regret captures variability induced by the instability of the learned tree structure itself. We provide a formal decomposition of observational multiplicity into these two components and establish statistical guarantees. Our experimental evaluation across diverse credit risk scoring datasets confirms the near-perfect alignment between our theoretical decomposition and the empirically observed variance. Notably, we find that structural regret is the primary driver of observational multiplicity, accounting for over 15 times the variability of leaf regret in some datasets. Furthermore, we demonstrate that utilizing these regret measures as an abstention mechanism in selective prediction can effectively identify arbitrary regions and improve model safety, elevating recall from 92% to 100% on the most stable sub-populations. These results establish a rigorous framework for quantifying observational multiplicity, aligning with recent advances in algorithmic safety and interpretability.

Ugur Dar, Mustafa Cavus

Predictive models often face performance degradation due to evolving data distributions, a phenomenon known as data drift. Among its forms, concept drift, where the relationship between explanatory variables and the response variable changes, is particularly challenging to detect and adapt to. Traditional drift detection methods often rely on metrics such as accuracy or variable distributions, which may fail to capture subtle but significant conceptual changes. This paper introduces drifter, an R package designed to detect concept drift, and proposes a novel method called Profile Drift Detection (PDD) that enables both drift detection and an enhanced understanding of the cause behind the drift by leveraging an explainable AI tool - Partial Dependence Profiles (PDPs). The PDD method, central to the package, quantifies changes in PDPs through novel metrics, ensuring sensitivity to shifts in the data stream without excessive computational costs. This approach aligns with MLOps practices, emphasizing model monitoring and adaptive retraining in dynamic environments. The experiments across synthetic and real-world datasets demonstrate that PDD outperforms existing methods by maintaining high accuracy while effectively balancing sensitivity and stability. The results highlight its capability to adaptively retrain models in dynamic environments, making it a robust tool for real-time applications. The paper concludes by discussing the advantages, limitations, and future extensions of the package for broader use cases.