article · Journal of risk and financial management
Frontier markets often lack tools to predict systemic stress because standard volatility models fail to capture structural breaks and regime shifts. To address this gap in Kenya, a multi-stage forecasting pipeline was created using historical daily data from the Nairobi Securities Exchange, currency exchange rates, and Brent oil prices between 1997 and 2024. The framework combines clustering, long-memory filtering, deep learning, and ensemble classification models. Testing different forecasting windows revealed that five-day predictions struck the best balance between reactivity and precision. Overall classification accuracy reached 0.98 using a hybrid ensemble combining long short-term memory networks and gradient boosting. The resulting system effectively categorises market conditions into calm, moderate, and stress regimes, translating signals into actionable early warning alarms that meet regulatory standards for tail-risk management.
Financial authorities and investors in frontier markets often struggle to anticipate sudden market shocks. By accurately forecasting shifts in market volatility, this system provides advance warning of financial stress. This allows regulators to intervene proactively, safeguard market stability, and better manage risk in environments prone to external economic pressures.
The framework has potential applications for financial regulators, central banks, and risk management teams within institutional investment firms operating in frontier markets. As an applied and validated analytical pipeline tested on historical Kenyan market data, it offers an evidence-backed methodology for stress detection. Further development would be required to integrate the pipeline into live trading software or real-time surveillance platforms.
AI-generated from the published abstract. Always read the original work before citing.
Frontier financial markets face a diagnostic gap in forecasting volatility: linear and single-regime GARCH fails to capture breaks, spillovers, and regime transitions. Despite the importance of these markets, there is a gap in the literature: lack of a Kenya-specific, regime-sensitive Early Warning System (EWS) that can integrate long-memory filtering of volatility with nonlinear classification models. Therefore, policymakers lack signals to anticipate systemic stress. This study constructed a multi-stage pipeline using 6703 daily observations of the NSE 20 Share Index, USD/KES exchange rate, and Brent spot prices (1997–2024). K-Means clustering, FIGARCH filtering, LSTM–XGBoost ensemble classification, a logistic threshold model, and VaR/ES back-testing were used to generate alarm signals and validate risk-management performance. Across model estimation and evaluation phases, time horizons were assessed, showing that one-day signals were reactive and ten-day forecasts diluted precision, while five-day predictions achieved the strongest balance. Across model iterations, accuracy improved from 0.86 in the initial FIGARCH–LSTM pipeline, to 0.92 in the unbalanced classification model, and 0.94 in the weighted baseline, culminating in 0.98 with the final hybrid LSTM–XGBoost ensemble. The ensemble model delivered robust detection across Calm (F1 = 0.99), Moderate (F1 = 0.82), and Stress (F1 = 0.69) regimes. Stress thresholds were developed to translate regime signals into actionable alarms. This study provides an empirical application of a hybrid framework, combining long memory modelling of volatility with the adaptability of deep learning models to deliver Basel-compliant tail-risk alarms and a state-dependent policy matrix for regulators.
This page summarises published work. The authoritative version sits with the publisher.
DOI: 10.3390/jrfm19090689
Is something wrong with this record? Report it or request removal.
Discussion
Have you built on this work, tried to replicate it, or seen it applied in practice? Share what you know. Verified researchers and MARATTO™ domain experts can open a discussion, and any member can reply. Contributions are reviewed before they appear.
No discussion yet. Open the first thread.
New to MARATTO™? Create a free account.
