Paper: arXiv 2402.03806

Authors: Marc Schmitt

Abstract

This paper explores the integration of Explainable Automated Machine Learning (AutoML) in the realm of financial engineering, specifically focusing on its application in credit decision-making. The rapid evolution of Artificial Intelligence (AI) in finance has necessitated a balance between sophisticated algorithmic decision-making and the need for transparency in these systems. The focus is on how AutoML can streamline the development of robust machine learning models for credit scoring, while Explainable AI (XAI) methods, particularly SHapley Additive exPlanations (SHAP), provide insights into the models’ decision-making processes. This study demonstrates how the combination of AutoML and XAI not only enhances the efficiency and accuracy of credit decisions but also fosters trust and collaboration between humans and AI systems. The findings underscore the potential of explainable AutoML in improving the transparency and accountability of AI-driven financial decisions, aligning with regulatory requirements and ethical considerations.

Complexity vs Empirical Score

  • Math Complexity: 4.0/10
  • Empirical Rigor: 7.0/10
  • Quadrant: Street Traders — empirical and applied, lower math complexity

Why this score: The paper leverages established statistical methods (GLMs, Random Forests, SHAP) without deriving novel theory, but demonstrates a practical, data-driven implementation using real-world datasets, AutoML frameworks (H2O), and validation metrics (AUC, log-loss).

Research Flowchart

  flowchart TD
  A["Research Goal:<br>Enhance Human-AI Collaboration<br>in Credit Decisions"] --> B["Methodology:<br>Explainable AutoML with SHAP"]
  
  B --> C["Input Data:<br>Financial/Credit Datasets"]
  
  C --> D["Computational Process:<br>AutoML Model Generation<br>+ SHAP Explanations"]
  
  D --> E["Output 1:<br>Automated Credit Scoring<br>with Improved Accuracy"]
  
  D --> F["Output 2:<br>Transparent Feature Explanations<br>for Human Review"]
  
  D --> G["Output 3:<br>Enhanced Trust & Collaboration<br>aligned with Regulations"]
  
  E & F & G --> H["Final Outcome:<br>Explainable AI-Driven<br>Credit Decision Framework"]

Evidence Card

What the authors claim, on what data, and who has checked it. Read from the paper's own text by a language model: every quote is verbatim, nothing was re-run. How to read this card

Proposes

The paper proposes integrating Explainable Automated Machine Learning (AutoML) with SHAP XAI methods to improve transparency, efficiency, and accuracy of credit decision‑making.

Source sentence
This study demonstrates how the combination of AutoML and XAI not only enhances the efficiency and accuracy of credit decisions but also fosters trust and collaboration between humans and AI systems.

Assumes 4

  • Random under‑sampling is used to balance the class distribution between good and bad credit applicants. data
    Source sentence
    To mitigate bias towards the majority class in this classification study, random under-sampling was employed to balance the dataset.
  • Categorical variables are converted to numeric form using one‑hot encoding. data
    Source sentence
    categorical values in the data were converted to numerical form using one-hot encoding
  • The publicly available Taiwan and Germany credit datasets accurately reflect information typically accessible to retail banks. data
    Source sentence
    These datasets are publicly accessible, facilitating the reproducibility of the empirical analysis.
  • The SHAP and variable importance heatmap visualisations are sufficient to provide guidance for human analysts to interpret model behaviour. model
    Source sentence
    Run explainability methods on the leaderboard (e.g. Shapley Values, Variable Importance Heatmap)

Data

  • Taiwan credit card dataset other public
    Source sentence
    Dataset 1 – Taiwan: The first dataset represents payment information from Taiwanese credit card clients. It was first used by Yeh and Lien (2009) and contains 30,000 observations where 6,636 are flagged as defaults.
  • Germany bank credit dataset other public
    Source sentence
    Dataset 2 – Germany: The second dataset represents detailed customer-level data from a German bank and contains 1,000 observations where 300 are flagged as defaults.

Costs

Not applicable The paper reports no trading or execution result.

Finds 2

  • Integrating AutoML with SHAP XAI methods yields more transparent and human‑centric credit scoring, bridging the gap between black‑box models and effective human‑AI collaboration. other
    Source sentence
    The integration of AutoML with explainable AI (XAI) methods, particularly using SHAP value plots and variable importance heatmaps, has illustrated the path towards more transparent, and human‑centric decision‑making in credit scoring.
  • Explainable AutoML provides visual guidance (SHAP plots, heatmaps) that supports analysts in interpreting model behavior and improves trust in AI‑driven credit decisions. other
    Source sentence
    Output: a set of visuals to provide guidance for human analysts to interpret model behavior, supporting informed decision-making and model validation.

Checked by others

Supported by

  • Explaining AI in Finance: Past, Present, Prospects (2023)
    On the question: Do SHAP-based XAI methods increase interpretability and user trust in AI-driven financial decision‑making?
    Compare the findings

    This paper: Explainable AutoML provides visual guidance (SHAP plots, heatmaps) that supports analysts in interpreting model behavior and improves trust in AI‑driven credit decisions.

    That paper: XAI techniques, such as SHAP values, improve interpretability of AI models and increase user trust in financial decision-making.

    Both findings report that SHAP visualizations (plots, heatmaps) improve model interpretability and boost trust in AI finance/credit decisions.

Cited by 2 papers in the archive (2 by independent authors)

Code

No repository by the authors found in the paper.

Extracted 2026-11-14 · same card as JSON · A language model chose these items: check the source sentence before relying on one.