United States banking stability: An explanation through machine learning

  • Received October 22, 2020;
    Accepted December 8, 2020;
    Published December 16, 2020
  • Author(s)
  • DOI
  • Article Info
    Volume 15 2020, Issue #4, pp. 137-149
  • Cited by
    5 articles

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

In this paper, an analysis of the prediction of bank stability in the United States from 1990 to 2017 is carried out, using bank solvency, delinquency and an ad hoc bank stability indicator as variables to measure said stability. Different machine learning assembly models have been used in the study, a random forest is developed because it is the most accurate of all those tested. Another novel element of the work is the use of partial dependency graphs (PDP) and individual conditional expectation curves (ICES) to interpret the results that allow observing for specific values how the banking variables vary, when the macro-financial variables vary.
It is concluded that the most determining variables to predict bank solvency in the United States are interest rates, specifically the mortgage rate and the 5 and 10-year interest rates of treasury bonds, reducing solvency as these rates increase. For delinquency, the most important variable is the unemployment rate in the forecast. The financial stability index is made up of the normalized difference between the two factors obtained, one for solvency and the other for delinquency. The index prediction concludes that stability worsens as BBB corporate yield increases.

view full abstract hide full abstract
    • Figure 1. MSE models
    • Figure 2a. Node purity increase vs. mse increase
    • Figure 2b. Times a root vs mean min. depth
    • Figure 3a. Times a root vs mean min. depth
    • Figure 3b. Node purity increase vs. mse increase
    • Figure 4a. Factors and differential
    • Figure 4b. Bank stability index
    • Figure 5. MSE (Bank stability Index)
    • Figure 6. Muti-way importance plot
    • Figure 7. ICEX curves e11
    • Figure 8. ICEX curves e9
    • Figure 9. ICEX curves e8
    • Figure 10a. Prediction of the forest (e8, e11)
    • Figure 10b. Prediction of the forest (e9, e11)
    • Figure 11a. ICE plot
    • Figure 11b. c-ICE plot
    • Figure 11c. d-ICE plot
    • Figure 12. e9, e10 and e11 predictions
    • Table 1. Variables
    • Table A1. Variables and factor structure
    • Conceptualization
      José Alejandro Fernández Fernández
    • Data curation
      José Alejandro Fernández Fernández
    • Formal Analysis
      José Alejandro Fernández Fernández
    • Investigation
      José Alejandro Fernández Fernández
    • Methodology
      José Alejandro Fernández Fernández
    • Project administration
      José Alejandro Fernández Fernández
    • Software
      José Alejandro Fernández Fernández
    • Supervision
      José Alejandro Fernández Fernández
    • Validation
      José Alejandro Fernández Fernández
    • Visualization
      José Alejandro Fernández Fernández
    • Writing – original draft
      José Alejandro Fernández Fernández
    • Writing – review & editing
      José Alejandro Fernández Fernández