Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Ntebogang Dinah Moroke has a total of 17 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    SpectralGuard: a Spectrally grounded λ-SHAP framework for XAI validity certification in pharmaceutical supply chain networks

    by Ntebogang Dinah Moroke, Mmapula Merriam Lebele

    Permutation-based explainability methods such as SHAP are central to regulatory compliance in AI-governed pharmaceutical supply chains across Sub-Saharan Africa, yet their validity depends on a structural property that existing frameworks do not monitor: the algebraic connectivity of the supply hypergraph, quantified by the Fiedler eigenvalue λ 2 . We prove that λ 2 → 0 is a sufficient condition for permutation-based XAI failure (Theorem 3.5): no increase in sampling effort can recover validity once network connectivity collapses. We introduce SpectralGuard, demonstrated on a calibrated synthetic DGP driven by real Eskom load-shedding and SARB ZAR/USD records ( n = 3, 227 business days, 2014–2026); all spectral results are from the synthetic hypergraph. λ-SHAP shrinks attributions toward a fluid-regime prior using λ 2 ( t ) as the shrinkage weight, maintaining auditability at an explicit bias–variance cost (Remark 3.12). A probabilistic validity certificate V ( t ) combines four spectral metrics with SHA-256 tamper-evidence. An oracle experiment ( B = 500, Seed = 2,026) demonstrates 70.4–89.2% attribution MSE reduction across governance regimes. The spectral gate is the decisive ablation component. In the synthetic DGP, early-warning detection leads classical baselines by 19 business days (λ c alert preceding the λ m crossing). Field validation on real CCMDD procurement data is planned for 2027 (PLMIF-2). A nine-step DHIS2 integration pathway supports SDG 3, 9, 13, and 16.

  • Open Access

    TENSORnet: a thermodynamically motivated entropy protocol for infrastructure-induced metabolic arrest detection in cross-asset financial networks

    by Ntebogang Dinah Moroke

    Conventional financial risk systems treat physical infrastructure as a fixed, frictionless background, an assumption that breaks down when electricity supply becomes binding. Markets then enter metabolic arrest : information-processing capacity collapses under a documented inversion between cross-asset correlation and entropy. TENSORnet (Temporal Entropy-aware Network for Systemic Onset Recognition) is a thermodynamically motivated protocol that fuses a VIX-calibrated inhibitory gate, grounded in Landauer’s energy-information bound, with cross-asset Shannon entropy. Rather than assuming architectural value, this study directly tests whether the protocol provides classification value beyond infrastructure-stage information alone. TENSORnet—applied to 2,838 JSE trading days (January 2015–April 2026) across seven asset classes under South Africa’s load-shedding crisis, using a three-way train/validation/test split motivated by the documented escalation history (Stage 4 first occurred February 2019)—achieves F1 = 99.55% and AUC = 0.9996 on the held-out test period (2020–2026, 1,581 days) at the primary Stage 3+ definition; a DeLong test finds this statistically indistinguishable from infrastructure-stage information alone ( p = 0.326 ) . Ablation confirms that the gate is load-bearing relative to purely market-based alternatives (AUC collapses to 0.568 without it; GARCH and network-connectedness achieve AUC ≤ 0.62), and the entropy layer outperforms a volatility-based substitute and a gradient-boosted benchmark under matched small-sample conditions, though it does not exceed the stage information itself. A cross-scale divergence signal, proposed as an advance-warning mechanism, is directly tested and does not survive (95% false alarm rate)—reported as a negative result. The densification paradox is empirically supported and confirmed via permutation testing against a mechanical-artefact null: rising cross-asset correlation accompanies falling entropy under infrastructure stress ( r = − 0.468 at Stage 4+ vs. r = − 0.184 at Stage 0, p < 0.001 )—this study’s most robust independent finding. A port-Hamiltonian neural ODE extension specifies an unvalidated conceptual pathway for future research. This study offers a disciplined example of testing, rather than assuming, whether a thermodynamically motivated architecture provides value beyond simpler alternatives, reporting results honestly where they complicate the original hypothesis.

  • Open Access

    A Maximum-Entropy Markov-Switching GARCH Framework: Information-Theoretic Bounds for Cryptocurrency Volatility Regime Detection

    by Ntebogang Dinah Moroke, Lebotsa Daniel Metsileng

    The distributional specification in Markov-switching GARCH (MS-GARCH) models has historically been driven by empirical convention. This paper derives the regime-conditional Student-t innovation distribution from the Tsallis Maximum Entropy Principle, providing an information-theoretic foundation for the choice of heavy-tailed innovations. The GARCH variance dynamics and Markov-switching structure are standard modelling choices adopted independently of the MaxEnt derivation. The framework is applied to five major cryptocurrencies over January 2017 to March 2026, comprising 15,824 daily observations. Three principal findings emerge. First, Tsallis entropy maximisation under a variance constraint yields the q-Gaussian density, which coincides with the Student-tνk distribution for qk=(νk+3)/(νk+1), with degrees of freedom determined endogenously from the empirical excess kurtosis. Second, calm-regime half-lives τC∈[1.21,2.37] days and stationary turbulent probabilities πT∈[0.254,0.437] confirm that both regimes are economically active across all assets; a Francq–Zakoïan stationarity verification confirms global ergodicity. Third, near-unity turbulent GARCH persistence suppresses the point-forecast advantage of regime-switching, consistent with a Fano-type Forecasting Irreversibility Bound; HAR-RV achieves the lowest QLIKE loss for three of five assets. Value-at-Risk backtests confirm adequate tail-risk calibration for four of five assets at the 1% and 5% levels, outperforming single-regime benchmarks. An empirical assessment of the VolShock extension identifies asset-class boundary conditions, motivating a proportional specification for future work.

  • Open Access

    HK-DeepIV: heat-kernel geometric diagnostics and early-warning signals for curvature-induced interference in financial correlation networks

    by Ntebogang Dinah Moroke

    Financial correlation networks under infrastructure shocks undergo curvature-driven interference that standard estimators cannot detect. This study introduces Heat-Kernel Deep Instrumental Variables (HK-DeepIV), a geometric diagnostic and early-warning framework modeling shock propagation as heat diffusion on the Riemannian manifold of Johannesburg Stock Exchange (JSE) asset-return correlations. Three formal results underpin the architecture: a non-parametric identification result for the projection of the structural function onto the leading heat-kernel eigenfunction ( k = 1; a scalar instrument can identify at most one linear combination of the eigenfunctions, and no claim is made beyond that projection); double robustness via Neyman orthogonality; and Corollary 3.2, showing that unit-level distinguishability collapses exponentially in diffusion time whenever Ollivier-Ricci curvature is positive; a purely geometric statement providing the basis for the fragility diagnostics developed here. Applied to 60 JSE tickers (2,832 trading days, 2015–2025) with Eskom load-shedding as the treatment (2022–2025), the trained model produces an ATE of +383 bp, reported as an overfitting artifact. Five independent baselines converge on smaller, mostly negative estimates. The most credibly conditioned conditional-association estimate is double machine learning [−20.75 bp, heteroskedasticity-and-autocorrelation-consistent (HAC)-corrected 95% CI [−51.62, 10.12] bp, p = 0.188], which is not significant at conventional levels; consistent with the instrument exogeneity caveat (5-day lagged return balance test, p = 0.007) and the descriptive framing of all estimates. The instrument [48-h-ahead Eskom stage forecast, Corr( Z t , D t )≈0.71, first-stage F = 47.3] is distinct from the treatment (realized Stage ≥2 binary), but exogeneity is not confirmed; all estimates are conditional associations. The Fiedler eigenvalue (mean 0.3827, minimum 0.1819) and mean Ollivier-Ricci curvature (0.5517, persistently positive) provide computable real-time fragility indicators. Across the four most severe load-shedding quarters, Fiedler and Ricci diagnostics offer comparable early-warning signals (mean lead-time difference −0.5 trading days); neither is systematically superior, but their combination is more informative than either alone. The framework contributes toward real-time spectral monitoring of infrastructure-driven systemic risk, supporting Uited Nations Sustainable Development Goal (UN SDG 9) in emerging markets.

  • Open Access

    MALP-Meta: An Empirical Evaluation of Maximum Agreement Linear Predictors for Directional Equity Market Forecasting

    by Ntebogang Dinah Moroke, Sharon Nwanamidwa, Olerato Makobea

    Typical machine learning forecasting approaches, optimized via mean squared error, struggle in decision settings requiring directional consistency. The Maximum Agreement Linear Predictor (MALP) framework addresses this by maximizing Lin’s Concordance Correlation Coefficient (CCC), but its meta-learner value under real, weak-signal conditions is untested. We evaluate a two-stage MALP-Meta architecture (four base models, a CCC-optimized meta-learner) on real hourly S&P 500 (SPY) data (n = 5032; 2023–2026), with every result cross-validated across two computing environments. Only Ridge achieves significant directional accuracy (52.7%, p = 0.037); no MALP-Meta variant improves on this, and we diagnose a previously undocumented pathology in which CCC optimization collapses toward a constant under weak signal. Of three temporal robustness strategies, only stable feature selection matches Ridge’s significance (52.5%, p = 0.048). Under an externally-defined stress regime (VIX>25), one meta-learner configuration improves simultaneously on concordance and direction, an unconfirmed signal (p = 0.291). Sensitivity analysis shows the primary result is fragile to the evaluation split. These findings affirm rather than overturn the conventional agreement–error trade-off: agreement-based meta-learning’s real-world value is modest, conditional on genuine market stress, and detectable only through rigorous cross-validation and sensitivity analysis.

  • Open Access

    A self-adaptive memetic algorithm with Lyapunov damping for stochastic OPF: evidence from South Africa's grid crisis

    by Ntebogang Dinah Moroke

    This study presents Lyapunov-SQP-MA (Lyapunov-guided Sequential Quadratic Programming Memetic Algorithm), a self-adaptive memetic algorithm that embeds an online stability estimator directly into the local Sequential Quadratic Programming (SQP) solver of a hybrid evolutionary optimizer. The central innovation is a closed-loop framework in which a finite-time local divergence rate ρ ^ k , computed via parallel shadow trajectory propagation, simultaneously controls the Levenberg–Marquardt damping parameter and validates the Damping–Stability Coupling Theorem in real-time. The theorem shows that the maximal Lyapunov exponent of the deterministic optimization skeleton increases (toward zero from below) with damping in the deterministic case, whereas the stochastic noise-amplification term strictly decreases with damping. Above a critical noise level, the full spectral bound decreases with damping, confirming that Lyapunov-guided damping provides a net stability benefit precisely when stochastic perturbations are large, and that the sufficient stabilizing threshold rises with noise amplitude. The online estimator operationalizes this result: its output drives a tanh-saturating feedback controller that self-adjusts regularization without manual re-tuning, and its observed behavior confirms the predicted coupling between detected instability and the need for increased damping across 35,064 hourly South African grid scenarios (2022–2025) spanning Eskom Stages 0–6. On IEEE 30-bus, 118-bus, and 300-bus benchmark systems, Lyapunov-SQP-MA achieves cost reductions of 0.20%–10.57%, 100% convergence success, and 39% variance reduction over the standard baseline. The monotone scaling of improvement with uncertainty level directly validates the Damping–Stability Coupling Theorem; ablation analysis confirms that the estimator is the decisive mechanism; and parameter sensitivity shows full robustness across a 3 × 3 controller grid without tuning. These results establish Lyapunov-guided adaptive damping as a principled mathematical framework for self-regulating optimization under stochastic perturbations, with direct applicability to large-scale energy dispatch and non-convex stochastic programming broadly.

  • Open Access

    Bayesian Spike-and-Slab Finite Mixture with Adaptive Tail Regularisation for Robust Volatility Regime Identification: Evidence from the Johannesburg Stock Exchange

    by Ntebogang Dinah Moroke, Sharon Nwanamidwa

    Volatility regime identification underpins risk management and portfolio allocation in quantitative finance, yet standard mixture models fail in heavy-tailed environments: components are consumed by outliers rather than genuine persistent regimes. We propose the Bayesian Spike-and-Slab Finite Mixture with Adaptive Tail Regularisation (BSS-FM-ATR), which resolves this at the component level via a spike-and-slab prior on the degrees-of-freedom parameter νk. A latent binary indicator assigns each component to a slab state (data-driven tail adaptation for genuine regimes) or a spike state (inert heavy-tail absorber for artefacts). Applied to 19 JSE blue-chip securities over December 2019 to December 2025—spanning the COVID-19 crash and Eskom load-shedding episodes—BSS-FM-ATR achieves the highest silhouette score (0.3809 on the full dataset), regime persistence (0.9391), and interpretability (0.800) across nine standard baselines, including Gaussian HMM, MS-AR, MS-GARCH(1,1), and Bayesian Changepoint detection, plus three outlier-component comparators (Contaminated–Normal Mixture, TCLUST, and robust Bayesian mixture). A complete rerun after removing the contaminated observations confirms that ARI (Δ=−0.0283) and persistence (Δ=+0.0105) remain stable; the silhouette reduction (from 0.3809 to 0.3773) is a positive finding: it confirms that the spike-state component R3 was correctly identified as a compact, well-separated artefact cluster whose removal reveals the genuine regime structure. This dual validation establishes BSS-FM-ATR’s role as both a regime identifier and a data quality filter. The method isolates a Yahoo Finance data-contamination artefact (n=21, January–February 2025) through a principled spike-and-slab mechanism, providing an explicit posterior probability p(γ3=0∣X)>0.99 of artefact status: a structural identifier that contaminated-normal and robust Bayesian alternatives cannot supply, establishing its value as both a regime identifier and a data quality filter for financial monitoring systems.

  • Open Access

    Deep Reinforcement Learning for Cryptocurrency Portfolio Management: A Free-Energy Framework with Geometry-Based Transaction Costs and Efficiency Bounds

    by Ntebogang Moroke

    This paper develops a deep reinforcement learning framework for cryptocurrency portfolio management in which transaction costs are derived from the Riemannian geometry of the underlying volatility model rather than assumed constant. A Proximal Policy Optimisation agent is trained on a reward function grounded in non-equilibrium thermodynamics: the free-energy Bellman equation, in which transaction costs are the geodesic slippage on the Fisher information manifold of a maximum-entropy Markov-switching GARCH model, and regime-transition costs are the Wasserstein-2 distance between the calm and turbulent return distributions. A thermodynamic Carnot bound on portfolio efficiency is established and empirically validated. Five hypotheses are tested across Bitcoin, Ethereum, Ripple, Litecoin, and Bitcoin Cash over January 2017 to March 2026. The geometric-cost agent achieves statistically superior Sharpe ratios relative to flat-fee baselines on four of five assets; portfolio turnover is reduced by 56 to 83 percent relative to signal-following; the thermodynamic friction point at which the agent prefers no-trade is asset-specific and ordered by turbulent half-life; a joint topological and geometric circuit breaker reduces Maximum Drawdown by 28 to 38 percent; and ablation confirms that every component of the observation vector contributes a statistically significant performance gain.


  • Open Access

    Fuzzy-Gated Stochastic Diffusion for Financial Regime Detection in Fractal Long-Memory Emerging Markets: The SARDINE Continuous-Time TSK Neuro-Fuzzy Framework

    by Ntebogang Dinah Moroke

    Financial markets in emerging economies exhibit fractal long-memory dynamics (H=0.93 on CBOE VIX; H=0.81 on JSE realised volatility) and extreme non-Gaussianity (kurtosis =51.6) that together invalidate conventional Gaussian-emission regime models. This paper introduces SARDINE (Stochastic Adaptive Regime Detection via Integrated Neuro-Fuzzy Estimation), a continuous-time framework that embeds Takagi-Sugeno-Kang (TSK) fuzzy membership weights directly inside a stochastic differential equation integrator, governing the geometry of stochastic uncertainty at each integration step. Three formal results underpin the architecture: a Lyapunov-style diffusion stability bound, a regime-adaptive noise attenuation guarantee, and an asymmetric cost advantage condition. Evaluated on 17 JSE Top40 securities (N=2778 daily observations, 2015–2026; 537-day held-out test), SARDINE achieves FAR =0.143, FNR =0.195, and a 1.33-day early-warning lead time, reducing the asymmetric cost by 32% relative to GMM. Against 14 baselines including Neural SDE, PatchTST, and Mamba, the fuzzy-gated diffusion reduces false alarms by 54–63%. A fractional Brownian motion ablation (H∈{0.44,0.50,0.93}, B=200 replicates) reveals that long-memory information should be embedded in the input representation rather than the noise driver; H=0.50 is recommended for operational deployment.

  • Open Access

    Cognitive Big Data Architecture for Daily Operational Jamming Transition Detection with Low-Latency Inference in Infrastructure-Constrained Financial Markets: The MERI Framework

    by Ntebogang Dinah Moroke

    We introduce the MERI (Market Evolutionary Resilience Index), a cognitive big data framework operationalising jamming transition physics into a daily operational regime detector (low-latency inference, 8 ms per observation). Opaque models cannot be deployed in regulated environments because every automated alert must decompose into auditable feature contributions. The MERI addresses this by treating the market as a complex adaptive system whose metabolic state constitutes the primary observable. Three cognitive layers fuse heterogeneous streaming data: an EGARCH-GED econometric baseline, a Random Forest classifier on a 15-dimensional physics-derived feature space, and a TreeSHAP Gini attribution audit ensuring full prediction-level transparency. Fisher Information Gain epistemic gating restricts automated intervention to predictions exceeding 2.5 nats certainty. Evaluated on South African financial markets (2015–2025, N=2870 trading days, Eskom load-shedding as exogenous forcing), the MERI achieves 97.3% accuracy (AUC = 0.9973, recall = 1.000), statistically equivalent to Temporal Fusion Transformers (Model Confidence Set, 90% confidence) while delivering 85.7% high-certainty predictions versus 23.4% for deep learning. A Granger-validated 48-h early warning lead (F=62.003, p<0.001), 7.78× recovery hysteresis (Cohen’s d=2.13), and infrastructure dominance of 78.0% (Gini) confirm that the framework is operationally feasible for daily monitoring in the South African JSE–Eskom setting. Cross-domain portability is proposed as a theoretical extension pending empirical validation.