Ntebogang Dinah Moroke

Prof. Dr. Ntebogang Dinah Moroke

Statistics and Operations Research, North-West Universtiy, Mahikeng, North West, South Africa
orcid
Open for collaboration in fractal finance & complexity

Research Focus & Metrics

Academic Career Length

13Years (2014-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
Verified
Journal Article
Open access
PDF file
Katleho MakatjaneKatleho Makatjane
Katleho Makatjane
NMNtebogang Dinah Moroke
Ntebogang Dinah Moroke
During the past decades, seasonal autoregressive integrated moving average (SARIMA) had become one of a prevalent linear models in time series and forecasting. Empirical research advocated that forecasting with non-linear models can be an encouraging alternative to traditional linear models. Linear models are often compared to non-linear models with mixed conclusions in terms of superiority in forecasting performance. Therefore, the aim of this study is to build an early warning system (EWS) model for extreme daily losses for financial stock markets. A logistic model tree (LMT) is used in collaboration with a seasonal autoregressive integrated moving average-Markov-Switching exponential generalised autoregressive conditional heteroscedasticity-generalised extreme value distribution (SARIMA-MS-EGARCH-GEVD) estimates. A time series of the study is a five-day financial time series exchange/Johannesburg stock exchange-all share index (FTSE/JSE-ALSI) for the period of 4 January 2010 to 31 July 2020. The study is set into a two-stage framework. Firstly, SARIMA model is fitted to stock returns in order to obtain independently and identically distributed (i.i.d) residuals and fit the MS(k)-EGARCH(p,q)-GEVD to i.i.d residuals; while, in the second stage, we set-up an EWS model. The results of the estimated MS(2)-EGARCH(1,1) -GEVD revealed that the conditional distribution of returns is highly volatile giving the expected duration to approximately 36 months and 4 days in regime one and 58 months and 2 days in regime two. We further found that any degree losses above 25% implies that there will be no further losses. Using the seven statistical loss functions, the estimated SARIMA(2,1,0)×(2,1,0)240−MS(2)−EGARCH(1,1)−GEVD proved to be the most appropriate model for predicting extreme regimes losses as it was ranked at 71%. Finally, the results of EWS model exhibit reasonably an overall performance of 98%, sensitivity of 79.89% and specificity of 98.40% respectively. The model further indicated a success classification rate of 89% and a prediction rate of 95%. This is a promising technique for EWS. The findings also confirmed 63% and 51% of extreme losses for both training sample and validation sample to be correctly classified. The findings of this study are useful for decision makers and financial sector for future use and planning. Furthermore, a base for future researchers for conducting studies on emerging markets, have been contributed. These results are also important to risk managers and and investors.

24 June 2022
Verified
Book Chapter
Closed access
NMNtebogang Dinah Moroke
Ntebogang Dinah Moroke
Katleho MakatjaneKatleho Makatjane
Katleho Makatjane
Financial fraud remains one of the most discussed topics in literature. The financial scandals of Enron, WorldCom, Qwest, Global Crossing, and Tyco resulted in approximately 460 billion dollars of loss. The detection of financial fraud, therefore, has become a critical task for financial practitioners. Three factors determine the likelihood of fraud occurrence, including pressure, opportunity, and rationalization. The core of these factors lies in people's beliefs and behaviour. Due to the unpredictability and uncertainty in fraudsters' incentives and techniques, fraud detection requires a skill set that encompasses both diligence and judgment. Big data technologies have had a huge impact on a wide variety of industries because they tend to be ubiquitous, starting in the last decade and continuing today. Request access from your librarian to read this chapter's full text.

1 November 2014 in Mediterranean Journal of Social Sciences
Verified
Journal Article
Open access
PDF file
NMNtebogang Dinah Moroke
Ntebogang Dinah Moroke
GLGontse Patricia Leballo
Gontse Patricia Leballo
DMDavid Mbathi Mello
David Mbathi Mello
Key intension of this paper was to verify Okun’s law in the South African perspective using data of the period 1990Q1 to 2013Q1. After detrending the series, the first lag and rank were used in the analysis to estimate Okun’s coefficient. The coefficients obtained were not in accordance with an acclaimed 3%. The short run model confirmed that a speed of 12.8% per quarter may be required to enable the system of unemployment rate in the country to be inverted back to normal. Toda-Yamamoto causality test reported no feedback associations between unemployment and GDP in SA. Empirically, evidence provides positive coefficients implying inapplicability of Okun’s law to South Africa. Nonetheless, unemployment still remains high according to the South African standards and it has to be dealt with amicably. The paper recommends to government and policy makers to up their games by employing economic policies that are more focused on to operational changes and makeover in workforce market. DOI: 10.5901/mjss.2014.v5n23p435

30 September 2014 in Journal of Economics and Behavioral Studies
Verified
Journal Article
Open access
PDF file
NMNtebogang Dinah Moroke
Ntebogang Dinah Moroke
This paper adopted the Box-Jenkins methodology to estimate a univariate time series model. Quarterly data collected from the South African Reserve Bank covering the period 1994 to 2014 was used. The initial plot of the series revealed that household debt is explained by an irregular and non-seasonal component. Owing to the non stationarity of the series, first differencing was applied to induce stationarity. The ACFs and PACFs identified six models. Of the six identified models,???????????????????? 3, 1, 0 was selected according to the standard error estimates and the information criteria. The proposed model passed all the diagnostic tests and was further used for producing ten period forecasts of household debt. The forecasted household debt rates obtained were above 75% and within confidence bounds of 95%. Insample and out-of-sampling forecasts moved together confirming the reliability of the model in forecasting household debt and vigour in predictive ability. The proposed model exhibited the best performance in terms of Max APE and Max AE and ascertained the robustness and accuracy of the BoxJenkins ARIMA in forecasting. Both a trend of the data captured and non-seasonal peaks were predicted by the model. These forecasts were proven to be realistic and a true reflection of economic reality in the country. The paper recommended a non-seasonal???????????????????? 3, 1, 0 be used by researchers, policy makers and decision makers of different countries to make forecasts of household debt. The South African authorities were also encouraged to use this model to produce further forecasts of the series when making long term planning.

2 May 2026 in Risks
Verified
Journal Article
Open access
PDF file
NMNtebogang Dinah Moroke
Ntebogang Dinah 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: we use 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. The framework requires liquid cryptocurrency markets with validated parametric volatility models; transferability to other asset classes requires upstream recalibration.

6 August 2018 in Journal of Statistics and Management Systems
Verified
Journal Article
Closed access
JTJohannes Tshepiso Tsoku
Johannes Tshepiso Tsoku
NMNtebogang Dinah Moroke
Ntebogang Dinah Moroke
This paper investigates the implementation of pairs trading strategy using correlation analysis and the Engle and Granger cointegration technique. The paper used financial sector traded on Johannesburg Stock Exchange (JSE). These data is for stock market comprising closing prices of option stock for 12 companies. The data was collected daily from 04 January 2010 to 31 December 2015. The findings of cointegration analysis confirmed only eighteen pairs shared a long run relationship. Since there is mean reversion, statistical arbitration strategy was implemented. The implementation of pairs trading to historical volatility revealed several possibilities of trade in the financial sector. Therefore, the investors would profit more from trading the identified pairs of stocks in the financial sector.