Thinawanga Hangwani Tshisikhawe

Mrs. Thinawanga Hangwani Tshisikhawe


Research Focus & Metrics

Academic Career Length

1Year (2026-Present)

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

Representative Publications

View All Publications
1 March 2026 in Computation
Verified
Journal Article
Open access
PDF file
RNRabelani Innocent NTHANGENI
Rabelani Innocent NTHANGENI
CSCaston Sigauke
Caston Sigauke
TRThakhani Ravele
Thakhani Ravele
TTThinawanga Hangwani Tshisikhawe
Thinawanga Hangwani Tshisikhawe
This paper presents probabilistic wind energy forecasting using quantile regression averaging combined with a conformal prediction modelling framework. The study uses data from Eskom, South Africa’s power utility company. The data is from April 2019 to November 2023. A partial linear additive quantile regression (PLAQR) averaging method is used to combine forecasts from two competing forecasting models: eXtreme Gradient Boosting (XGBoost) and Principal Component Regression (PCR). To compare the predictive abilities of the models, two data splits are used: 80%, 10% and 10% for the first set, and 85%, 10% and 5% for the second set, for training, validation and testing, respectively. Empirical results suggest that the combined predictions from PLAQR perform better than the individual models, significantly improving calibration and accuracy. The proposed combination has the smallest root mean square error (RMSE) and the highest probability of change in direction (POCID). The combination captures nonlinearities and produces well-calibrated probabilistic results. Probability integral transform histograms validate this. This performance gain reflected the importance of data volume. This is reinforced by the fact that the PLAQR model, which combines the benefits of tree-based approaches and linear models, is a robust modelling approach for reliable renewable energy forecasting. Future research directions should consider more varied ensembles.

4 April 2026 in Economies
Verified
Journal Article
Open access
PDF file
FMFhulufhedzani Justice Madega
Fhulufhedzani Justice Madega
TTThinawanga Hangwani Tshisikhawe
Thinawanga Hangwani Tshisikhawe
TRThakhani Ravele
Thakhani Ravele
CSCaston Sigauke
Caston Sigauke
This paper compares the daily return volatility by four leading international indices: JSE Top 40, FTSE 100, Nikkei 225 and S&P/ASX 200. The return series are modelled in ARMA process, where ARMA(1,3) values are taken for JSE Top 40 and S&P/ASX 200, ARMA(0,0) for FTSE 100, and ARMA(1,2) for Nikkei 225. The volatility is modelled in APARCH and GJR-GARCH (e.g., under various conditional distributions including Student-t (STD), skewed Student-t (SSTD), generalised error distribution (GED), skewed generalised error distribution (SGED), and generalised hyperbolic distribution (GHYD)). Model selection results based on information criteria indicate that the APARCH models outperform their GJR-GARCH counterparts in all cases. In particular, the ARMA(p,q)-APARCH(1,1) with SSTD is most suitable for the JSE Top 40 and the FTSE 100. The model that best describes the Nikkei 225 is an ARMA(1,2)–APARCH(1,1) model with SGED, and the S&P/ASX 200 fits an ARMA(1,3)-APARCH(1,1) model with GHYP. Among the indices, the FTSE 100 has the highest volatility persistence, while the Nikkei 225 responds more quickly to shocks. This out-of-sample forecasting test shows that ARMA(p,q)-APARCH(p,q) provides more accurate volatility predictions, especially for JSE Top 40 and S&P/ASX 200 investors.

23 January 2026 in Preprints.org
Verified
Preprint
Open access
PDF file
RNRabelani Innocent NTHANGENI
Rabelani Innocent NTHANGENI
CSCaston Sigauke
Caston Sigauke
TRThakhani Ravele
Thakhani Ravele
TTThinawanga Hangwani Tshisikhawe
Thinawanga Hangwani Tshisikhawe
This paper presents probabilistic wind energy forecasting using quantile regression averaging combined with a conformal prediction modelling framework. The study uses data from Eskom, South Africa's power utility company. The data is from April 2019 to November 2023. A partial linear additive quantile regression (PLQR) averaging method is used to combine forecasts from two competing forecasting models: eXtreme Gradient Boosting (XGBoost) and Principal Component Regression (PCR). To compare the predictive abilities of the models, two data splits are used: 80\%, 10\% and 10\% for the first set, and 85\%, 10\% and 5\% for the second set. Empirical results suggest that the combined predictions from PLAQR perform better than the individual models, significantly improving calibration and accuracy. The proposed combination has the smallest root mean square error (RMSE) and the highest probability of change in direction (POCID). The combination captures nonlinearities and produces well-calibrated probabilistic results. Probability integral transform histograms validate this. This performance gain reflected the importance of data volume. This is reinforced by the fact that the PLAQR model, which combines the benefits of tree-based approaches and linear models, is a robust modelling approach for reliable renewable energy forecasting. Future research directions should consider more varied ensembles.

22 April 2026 in Risks
Verified
Journal Article
Open access
PDF file
SFSthembile albertinah Fundama
Sthembile albertinah Fundama
TRThakhani Ravele
Thakhani Ravele
TTThinawanga Hangwani Tshisikhawe
Thinawanga Hangwani Tshisikhawe
CSCaston Sigauke
Caston Sigauke
Using daily data from Investing.com South Africa, this study investigates the forecasting performance of four Rand currency rate markets (EUR/ZAR, CHF/ZAR, BRL/ZAR, and CNY/ZAR) from 13 February 2018 until 24 February 2025. The predictive fitness of three competing models, Support Vector Regression (SVR), Principal Component Regression (PCR), and eXtreme Gradient Boosting (XGBoost), is explored between 80%/20% and 95%/5% training-testing splits. Forecasting accuracy is evaluated based on evaluation errors, i.e., Mean Absolute Error (MAE) and Root Mean Square Error (RMSE). The Diebold–Mariano test is employed to check for statistical significance. Empirical results show that the linear SVR model outperforms PCR across all markets, while XGBoost achieves competitive predictive accuracy on average; the trade-offs between SVR and XGBoost are often very small. The data indicate that linear kernel methods provide a robust prediction pipeline, especially when macroeconomic factors (gold, oil, platinum prices, and the USD/ZAR exchange rate) and calendar-based factors are taken into account, and offer a strong framework for predicting daily exchange rate fluctuations. The results of this research provide practitioners (traders, risk managers, and policymakers) with insights into the relative efficiency of the kernel vs. ensemble learning approaches for forecasting the value of emerging-market currencies in the presence of structural volatility.

3 March 2026 in Preprints.org
Verified
Preprint
Open access
PDF file
TTThinawanga Hangwani Tshisikhawe
Thinawanga Hangwani Tshisikhawe
CSCaston Sigauke
Caston Sigauke
TDTimotheus Darikwa
Timotheus Darikwa
SNSaralees Nadarajah
Saralees Nadarajah
Accurate wind speed forecasting is critical for renewable energy planning and meteorological studies. However, wind behaviour is complex due to the presence of synoptic systems, terrain effects, and turbulence. This paper proposes a new model that uses a linear regression mean model and a Gaussian process for residual modelling. The monitoring stations were clustered by geographic coordinates and elevation. The Hopkins statistic was employed for cluster validation, while silhouette values were employed for cluster quality validation. It was found that for stations at high elevation located in the interior (Cluster 2), the GP model for residual modelling consistently improved wind forecast accuracy by up to 16.3%. However, for coastal stations at low elevation (Cluster 1), the GP model was not effective for residual modelling. This proves that the accuracy of GP residual modelling depends to a large extent on the wind regime.

26 April 2026 in Forecasting
Verified
Journal Article
Open access
PDF file
TTThinawanga Hangwani Tshisikhawe
Thinawanga Hangwani Tshisikhawe
CSCaston Sigauke
Caston Sigauke
TDTimotheus Darikwa
Timotheus Darikwa
SNSaralees Nadarajah
Saralees Nadarajah
Accurate wind speed forecasting is essential for the efficient integration of wind energy into power systems, as it directly influences generation scheduling, grid stability, and energy market operations. Forecast errors can lead to significant economic losses, including increased balancing costs, inefficient dispatch of backup generation, and penalties in electricity markets. However, wind behaviour is highly complex due to the influence of synoptic weather systems, terrain variability, and turbulence, which makes accurate prediction particularly challenging. This paper proposes a hybrid modelling framework that combines a linear regression mean model with Gaussian process (GP) residual modelling to improve forecast accuracy. Monitoring stations were grouped based on geographic coordinates and elevation, with cluster validation using the Hopkins statistic and silhouette analysis. The results show that for high-elevation inland stations (cluster 2), GP residual modelling improves forecast accuracy by up to 16.3%. In contrast, for low-elevation coastal stations (cluster 1), the GP approach does not yield improvements, indicating that its effectiveness depends strongly on the underlying wind regime.