Explainable Artificial Intelligence Uncovers Non-Bank Financial Industry Contagion and Safeguards Central Bank Institutional Governance

Introduction/Main Objectives: This paper examines systemic risk interconnections within Indonesia's Non-Bank Financial Industry (NBFI), which displays intricate systemic risk interconnections that alter traditional macroprudential dynamics. As financial ecosystems digitalize, understanding cross-sectoral risk transmission beyond banking is crucial for stability. The study further aims to develop a transparent artificial intelligence framework capable of supporting timely macroprudential policy interventions and institutional decision-making. Background Problems: Systemic risk from NBFI interconnections insurance, pension funds, finance companies, guarantee institutions, and P2P lending remains insufficiently mapped, and linear models fail to capture nonlinear contagion, raising the question of how risks transmit across NBFI sectors and what their primary drivers are. Novelty: This paper pioneers integrating econometrics with Explainable AI (SHAP-Random Forest) to construct an NBFI systemic risk framework, offering transparent, actionable insights for regulators to strengthen macroprudential governance and safeguard financial stability. Research Methods: The study employs correlation analysis, Granger causality, OLS regression, and Random Forest with SHAP decomposition using Indonesian NBFI sectoral data (2016–2024). Finding/Results: Results reveal strong cross-sectoral risk linkages and nonlinear transmission, identifying pension fund asset size and foreign funding exposures as dominating cross-sectoral systemic risk, contributing mean SHAP values of 0.576 and 0.326, respectively. During COVID-19, NBFI sectors acted as shock absorbers rather than amplifiers. Conclusion: The findings underscore the need for Algorithmic Macroprudential Governance, where explainable AI enhances evidence-based supervision, strengthens institutional autonomy, improves systemic risk monitoring in emerging financial architectures, and provides actionable insights for regulators in safeguarding long-term financial stability.

Authors

Publication Details

Journal
Banking & Management Review
Published
2026-11-19
DOI
https://doi.org/10.52250/bmr.v14i2.1152
Primary Topic
Banking stability, regulation, efficiency
Type
article
Field-Weighted Citation Impact
0.00
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
NOV
article

Explainable Artificial Intelligence Uncovers Non-Bank Financial Industry Contagion and Safeguards Central Bank Institutional Governance

Mochamad Fatchurrohman, Iman Supriadi, Rizyana Mirda
Banking & Management Review
Banking stability, regulation, efficiency
article

Explainable Artificial Intelligence Uncovers Non-Bank Financial Industry Contagion and Safeguards Central Bank Institutional Governance

Mochamad Fatchurrohman, Iman Supriadi, Rizyana Mirda
article en

Abstract

Introduction/Main Objectives: This paper examines systemic risk interconnections within Indonesia's Non-Bank Financial Industry (NBFI), which displays intricate systemic risk interconnections that alter traditional macroprudential dynamics. As financial ecosystems digitalize, understanding cross-sectoral risk transmission beyond banking is crucial for stability. The study further aims to develop a transparent artificial intelligence framework capable of supporting timely macroprudential policy interventions and institutional decision-making. Background Problems: Systemic risk from NBFI interconnections insurance, pension funds, finance companies, guarantee institutions, and P2P lending remains insufficiently mapped, and linear models fail to capture nonlinear contagion, raising the question of how risks transmit across NBFI sectors and what their primary drivers are. Novelty: This paper pioneers integrating econometrics with Explainable AI (SHAP-Random Forest) to construct an NBFI systemic risk framework, offering transparent, actionable insights for regulators to strengthen macroprudential governance and safeguard financial stability. Research Methods: The study employs correlation analysis, Granger causality, OLS regression, and Random Forest with SHAP decomposition using Indonesian NBFI sectoral data (2016–2024). Finding/Results: Results reveal strong cross-sectoral risk linkages and nonlinear transmission, identifying pension fund asset size and foreign funding exposures as dominating cross-sectoral systemic risk, contributing mean SHAP values of 0.576 and 0.326, respectively. During COVID-19, NBFI sectors acted as shock absorbers rather than amplifiers. Conclusion: The findings underscore the need for Algorithmic Macroprudential Governance, where explainable AI enhances evidence-based supervision, strengthens institutional autonomy, improves systemic risk monitoring in emerging financial architectures, and provides actionable insights for regulators in safeguarding long-term financial stability.

Banking & Management ReviewVol. 14(2)
Banking stability, regulation, efficiency
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.

Laika access coming soon