Application of AI in Credit Risk Scoring for Small Business Loans: A case study on how AI-based random forest model improves a Delphi model outcome in the case of Azerbaijani SMEs

Paper: arXiv 2410.05330

Authors: Nigar Karimova

Abstract

The research investigates how the application of a machine-learning random forest model improves the accuracy and precision of a Delphi model. The context of the research is Azerbaijani SMEs and the data for the study has been obtained from a financial institution which had gathered it from the enterprises (as there is no public data on local SMEs, it was not practical to verify the data independently). The research used accuracy, precision, recall and F-1 scores for both models to compare them and run the algorithms in Python. The findings showed that accuracy, precision, recall and F- 1 all improve considerably (from 0.69 to 0.83, from 0.65 to 0.81, from 0.56 to 0.77 and from 0.58 to 0.79, respectively). The implications are that by applying AI models in credit risk modeling, financial institutions can improve the accuracy of identifying potential defaulters which would reduce their credit risk. In addition, an unfair rejection of credit access for SMEs would also go down having a significant contribution to an economic growth in the economy. Finally, such ethical issues as transparency of algorithms and biases in historical data should be taken on board while making decisions based on AI algorithms in order to reduce mechanical dependence on algorithms that cannot be justified in practice.

Complexity vs Empirical Score

• Math Complexity: 2.5/10
• Empirical Rigor: 5.0/10
• Quadrant: Street Traders — practical and empirical, lighter on theory

Why this score: The paper provides a standard empirical application of Random Forest models to compare against traditional scoring methods for Azerbaijani SMEs. While it provides metric improvements ( accuracy, precision, recall) and sample Python code in appendices, the mathematical depth is very low and relies on standard high-level off-the-shelf ML algorithms.

Research Flowchart

  flowchart TD
    A[<b>Research Goal:</b> Improve Delphi Credit Risk Model for Azerbaijani SMEs using AI] --> B[<b>Data Collection:</b> SME Financial Institution Data]
    B --> C[<b>Methodology & Processing:</b> Implement Random Forest Model in Python]
    C --> D[<b>Model Evaluation:</b> Compare Delphi vs. Random Forest on Accuracy, Precision, Recall, F1]
    D --> E[<b>Key Findings:</b> All metrics improved significantly <br><i>e.g., Accuracy: 0.69 → 0.83, F1: 0.58 → 0.79</i>]
    E --> F[<b>Outcomes & Impact:</b> Reduced credit risk, fewer unfair SME rejections, <br>need to address algorithmic bias & transparency]

Cited References (1)

1. A novel credit scoring model based on optimized random forest (2018) — link

0 of 1 cited works are in the corpus; resolved via arXiv source bundles, Semantic Scholar and OpenAlex. Corpus-wide: 2518 linked papers.