Development of a Bankruptcy Prediction Model for the Banking Sector in Mozambique Using Linear Discriminant Analysis

Paper: arXiv 2311.16705

Authors: Reis Castigo Intupo

Abstract

In Mozambique there is no evidence of a bankruptcy prediction model developed in the national economic context, yet, back in 2016, the national banking sector suffered a financial shock that resulted in Mozambique Central Bank intervention in two banks (Moza Banco, S.A. and Nosso Banco, S.A.). This was a result of the deterioration of their financial and prudential indicators, although Mozambique had been adhering to the Basel Accords since 1994. The Basel Accords provides recommendations on banking sector supervision worldwide with the aim to enhance financial system stability. While it does not predict bankruptcy, the prediction model can be used as an auxiliary tool to manage that risk, but this has to be built in the national economic context. This paper develops for Mozambique banking sector a bankruptcy prediction model in the Mozambican context through the linear discriminant analyses method, following two assumptions: (i) composition of the sample and (ii) robustness of the financial prediction indicators (the capital structure, profitability asset concentration and asset quality) from 2012 to 2020. The developed model attained an accuracy level of 84% one year before Central Bank intervention (2015) with the entire population of 19 banks of the sector, which makes it recommendable as a risk management tool for this sector.

Complexity vs Empirical Score

• Math Complexity: 3.5/10
• Empirical Rigor: 5.0/10
• Quadrant: Street Traders — practical and empirical, lighter on theory

Why this score: The paper applies standard Linear Discriminant Analysis (LDA) to a small, localized dataset of 19 banks in Mozambique to build an country-specific bankruptcy model. While it offers practical regional value and decent empirical application, the underlying mathematical framework relies on established classical techniques without methodological innovation.

Research Flowchart

  flowchart TD
    A[Research Goal: Develop Bankruptcy Prediction Model for Mozambican Banking Sector] --> B[Data Collection: Financial & Prudential Indicators 2012-2020 for 19 Banks]
    B --> C[Data Categorization: Capital Structure, Profitability, Asset Quality & Concentration]
    C --> D[Methodology: Apply Linear Discriminant Analysis Method]
    D --> E[Model Validation: Test Prediction Accuracy for 2016 Central Bank Interventions]
    E --> F[Key Outcome: Achieved 84% Accuracy 1-Year Prior to Intervention]
    F --> G[Recommendation: Auxiliary Risk Management & Banking Supervision Tool]