6 papers
Counterfactual Explanations Under Concept Drift
Marcin Kostrzewa, Jerzy Stefanowski, Maciej ZiÄba
Counterfactual explanations (CFEs) provide actionable recourse, but most methods assume a static framework with fixed data and a trained classifier. This assumption breaks in evolv…
V4FinBench: Benchmarking Tabular Foundation Models, LLMs, and Standard Methods on Corporate Bankruptcy Prediction
Marcin Kostrzewa, Sebastian Tomczak, Roman Furman +5
Corporate bankruptcy prediction is a high-stakes financial task characterized by severe class imbalance and multi-horizon forecasting demands. Public datasets supporting it remain…
A Probabilistic Consensus-Driven Approach for Robust Counterfactual Explanations
Marcin Kostrzewa, Maciej ZiÄba, Jerzy Stefanowski
Counterfactual explanations (CFEs) are essential for interpreting black-box models, yet they often become invalid when models are slightly changed. Existing methods for generating…
Towards plausibility in time series counterfactual explanations
Marcin Kostrzewa, Krzysztof Galus, Maciej ZiÄba
We present a new method for generating plausible counterfactual explanations for time series classification problems. The approach performs gradient-based optimization directly in…
Are Foundation Models Useful for Bankruptcy Prediction?
Marcin Kostrzewa, Oleksii Furman, Roman Furman +2
Foundation models have shown promise across various financial applications, yet their effectiveness for corporate bankruptcy prediction remains systematically unevaluated against e…
CINNAMON: A hybrid approach to change point detection and parameter estimation in single-particle tracking data
Jakub Malinowski, Marcin Kostrzewa, MichaÅ Balcerek +2
Change point detection has become an important part of the analysis of the single-particle tracking data, as it allows one to identify moments, in which the motion patterns of obse…