A Data-driven Case-based Reasoning in Bankruptcy Prediction
Proposes a data-driven explainable case-based reasoning system for bankruptcy prediction, improving accuracy and interpretability.
What it examines
This study proposes a data-driven explainable case-based reasoning (CBR) system for bankruptcy prediction, aiming to enhance both accuracy and interpretability. The approach leverages asymmetrical feature similarity comparison to capture the uneven distribution of financial attributes, addressing the challenge of imbalanced, high-dimensional, nonlinear classification problems in bankruptcy prediction.
What it concludes
The study concludes that the proposed CBR system effectively predicts bankruptcy while providing interpretability, aiding stakeholders in decision-making. Potential applications include financial risk detection and decision support in bankruptcy-related scenarios. Future research could explore optimal feature weight detection and system maintenance cost minimization.
Evidence objects
The study concludes that the proposed CBR system effectively predicts bankruptcy while providing interpretability, aiding stakeholders in decision-making. Potential applications include financial risk detection and decision support in bankruptcy-related scenarios. Future research could explore optimal feature weight detection and system maintenance cost minimization.
key_findings bullet 1 · key_findings · validation V0
Raw abstract and provenance
Abstract: There has been intensive research regarding machine learning models for predicting bankruptcy in recent years. However, the lack of interpretability limits their growth and practical implementation. This study proposes a data-driven explainable case-based reasoning (CBR) system for bankruptcy prediction. Empirical results from a comparative study show that the proposed approach performs superior t… ▽ More There has been intensive research regarding machine learning models for predicting bankruptcy in recent years. However, the lack of interpretability limits their growth and practical implementation. This study proposes a data-driven explainable case-based reasoning (CBR) system for bankruptcy prediction. Empirical results from a comparative study show that the proposed approach performs superior to existing, alternative CBR systems and is competitive with state-of-the-art machine learning models. We also demonstrate that the asymmetrical feature similarity comparison mechanism in the proposed CBR system can effectively capture the asymmetrically distributed nature of financial attributes, such as a few companies controlling more cash than the majority, hence improving both the accuracy and explainability of predictions. In addition, we delicately examine the explainability of the CBR system in the decision-making process of bankruptcy prediction. While much research suggests a trade-off between improving prediction accuracy and explainability, our findings show a prospective research avenue in which an explainable model that thoroughly incorporates data attributes by design can reconcile the dilemma. △ Less
Source row: 13 · abstract type: unknown