Risk management through a Kohonen map bank business model survey: The case of Ukraine

  • 95 Views
  • 14 Downloads

Creative Commons License
This work is licensed under a Creative Commons Attribution 4.0 International License

The purpose of this paper is to identify the peculiarities of banks’ business models and assess their risks, which is especially relevant in the context of the war in Ukraine since 2014. The information base is the published statements for each month of 63 Ukrainian banks for the period from 1 January 2018 to 1 January 2024. The number of indicators is chosen in an empirical manner. Business models are investigated using the method of structural-functional groups of banks, which allows estimating large arrays of financial indicators, grouping banks with similar characteristics and drawing conclusions about the main risks. It is convenient to use neural networks, namely Kohonen’s self-organizing maps, to estimate large data sets. The largest group of banks places a significant part of assets in government securities and has an unstable resource base. The share of these banks in the system as of January 1, 2024 is 38% and total assets are 10%. The second group by number of banks is focused on corporate lending with a high share of current resources in liabilities, and includes 21% of banks, whose assets account for 31% of total assets. State-owned banks, PrivatBank and OschadBank, account for 35% of total assets. The business models of these banks are characterized by dependence on retail funds, a high share of investment operations, and high credit and currency risks. Ukraine’s banking system has significantly developed a risk-oriented approach to management, which allowed it to maintain stability in the face of a full-scale war.

view full abstract hide full abstract
    • Figure 1. Kohonen map as of January 1, 2024
    • Figure 2. Distribution of values of the loan portfolio structure indicators
    • Figure 3. Distribution of investment portfolio structure indicators
    • Figure 4. Distribution of values of the legal persons’ liability structure indicators
    • Figure 5. Distribution of indicator values of the natural persons’ liability structure
    • Figure 6. Distribution of indicator values of banks’ profitability sources
    • Figure 7. Dynamics of Ukrainian banks’ average profitability indicators
    • Figure 8. Example of concentration of the highest level of SAFN and SPFN indicators of individuals’ attracted and placed funds in the group of retail banks
    • Figure 9. Example of concentration of the highest level of indicators of interbank funds attracted by SPMI and reserves RA in a group of problem banks
    • Table 1. SFGB indicators as of January 1, 2024, %
    • Table 2. Indicators of the asset structure as of January 1, 2024
    • Table 3. Indicators of the structure of liabilities as of January 1, 2024
    • Table 4. Characteristics of SFGBs as of January 1, 2024
    • Table 5. Other indicators of bank clustering as of January 1, 2024
    • Conceptualization
      Olena Zarutska, Olena Dobrovolska
    • Data curation
      Olena Zarutska, Ralph Sonntag, Wolfgang Ortmanns
    • Formal Analysis
      Olena Zarutska, Olena Dobrovolska, Iuliia Masiuk, Ralph Sonntag
    • Funding acquisition
      Olena Zarutska
    • Investigation
      Olena Zarutska, Wolfgang Ortmanns
    • Methodology
      Olena Zarutska, Iuliia Masiuk
    • Project administration
      Olena Zarutska, Olena Dobrovolska, Iuliia Masiuk
    • Resources
      Olena Zarutska
    • Software
      Olena Zarutska
    • Supervision
      Olena Zarutska, Ralph Sonntag
    • Visualization
      Olena Zarutska, Iuliia Masiuk, Ralph Sonntag, Wolfgang Ortmanns
    • Writing – original draft
      Olena Zarutska, Olena Dobrovolska, Iuliia Masiuk, Ralph Sonntag, Wolfgang Ortmanns
    • Writing – review & editing
      Olena Zarutska, Olena Dobrovolska, Iuliia Masiuk, Ralph Sonntag, Wolfgang Ortmanns
    • Validation
      Wolfgang Ortmanns