Search Results (35)

This study applies Gradient Boosting Machines (GBMs) and principal component regression (PCR) to forecast the closing price of the Johannesburg Stock Exchange (JSE) All-Share Index (ALSI), using daily data from 2009 to 2024, sourced from the Wall Street Journal. The models are evaluated under three training–testing split ratios to assess short-term forecasting performance. Forecast accuracy is assessed using standard error metrics: mean absolute error (MAE), root mean square error (RMSE), mean absolute percentage error (MAPE), and mean absolute scaled error (MASE). Across all test splits, the GBM consistently achieves lower forecast errors than PCR, demonstrating superior predictive accuracy. To validate the significance of this performance difference, the Diebold–Mariano (DM) test is applied, confirming that the forecast errors from the GBM are statistically significantly lower than those of PCR at conventional significance levels. These findings highlight the GBM’s strength in capturing nonlinear relationships and complex interactions in financial time series, particularly when using features such as the USD/ZAR exchange rate, oil, platinum, and gold prices, the S&P 500 index, and calendar-based variables like month and day. Future research should consider integrating additional macroeconomic indicators and exploring alternative or hybrid forecasting models to improve robustness and generalisability across different market conditions. Full article

The relationship between ESG and firm performance is complex and tends to yield mixed results globally. In South Africa, ESG implementation is still in its infancy stage due to economic and developmental challenges. Despite these challenges, the JSE introduced sustainability disclosure guidelines in 2022 to enhance ESG adoption in South Africa. Thus, the study seeks to understand the impact of ESG and firm size on the financial performance of JSE-listed firms in South Africa. The study utilised the JSE Top 40 firms for the period from 2002 to 2022. Furthermore, the study employed a two-step System Generalised Method of Moments, to estimate the impact of total ESG and individual dimensions of ESG on firm financial performance. Additionally, the study examined the moderating effects of firm size on the relationship between financial performance and ESG. The results revealed a positive and significant relationship between total ESG and firm financial performance. However, the findings regarding individual ESG dimensions and firm performance are mixed. Firm size has a moderating effect on the relationship between ESG and firm financial performance. The implication of these findings for South Africa is increased foreign direct investment from green investors and listed firms seriously considering ESG in their operations. Full article

This study investigates the relationship between corporate social responsibility performance and financial performance among firms listed on the Johannesburg Stock Exchange in South Africa. Utilising a multi-metric approach, the research incorporates corporate social responsibility scores; environmental, social, and governance ratings; and the social pillar score to provide a comprehensive analysis. Data from 104 companies with 624 observations from 2017 to 2022 was analysed. This quantitative study employs a Generalised Least Squares estimation, and the findings reveal a significant positive correlation between corporate social responsibility performance and several key financial metrics, including return on assets, earnings per share, market value added, and Tobin’s Q ratio. The results suggest that companies prioritising corporate social responsibility initiatives are likely to experience improved financial outcomes. Furthermore, the study examines the influence of board characteristics on financial performance, identifying a positive effect of gender diversity and negative impacts from board independence and meeting frequency. Overall, this research contributes to the literature on corporate social responsibility and financial performance by highlighting the importance of corporate social responsibility in driving sustainable business practices and enhancing firm performance within the context of an emerging economy. The findings underscore the need for firms to integrate corporate social responsibility into their strategies to promote long-term success while addressing societal challenges. Full article

The objective of the study is to examine the effects of investor sentiment on the Johannesburg Stock Exchange (JSE) index returns in bull and bear market conditions. Accordingly, this study uses monthly data to construct a new market-wide investor sentiment index and test its effects on the JSE aggregated and disaggregated index returns in alternating market conditions for the period March 2007 to January 2024. The findings of the Markov regime-switching model reveal that when the JSE is in a bull market condition, the JSE oil and gas sector returns and the JSE telecommunication sector returns are affected positively by investor sentiment. Similarly, in a bearish state, the JSE health sector returns and JSE telecommunication sector returns are negatively affected by investor sentiment. Collectively, the findings suggest that the effects of investor sentiment on JSE index returns are regime-specific and time-varying, such that they are dependent on the market conditions (bull or bear) and the type of JSE index (aggregated or disaggregated index). Accordingly, investors must consider this information to ensure resilient investment decisions and risk management strategies in sentiment-induced markets and alternating market conditions. Full article

The stability of financial markets is influenced by the strength and transparency of companies listed on stock exchanges. This paper explores how financial, non-financial, and macroeconomic factors influence delisting likelihood among companies listed on the Johannesburg Stock Exchange (JSE), addressing a limitation in the current body of knowledge that often overlooks the combination of these factors, especially within the context of developing economies. Using a sample of 302 companies delisted between 2010 and 2023 and 302 as a control group, we analyzed 72 variables through a multivariate panel probit regression model. Our findings reveal that delisting decisions are driven by a complex interplay of financial health, governance practices, and macroeconomic conditions. Financial health, including liquidity and market valuation, is crucial in mitigating delisting risk. Non-financial factors, such as corporate governance and shareholder composition, further reduce the likelihood of delisting. Macroeconomic conditions, including inflation and interest rates, introduce significant external pressures. This study is especially relevant in developing economies like South Africa, where economic volatility adds risks for listed companies. The results provide insights for companies, investors, regulators, and policymakers to ensure a stable and robust stock market and financial system and identify early warning signals for delisting. Full article

In numerous domains of finance and economics, modelling and predicting stock market volatility is essential. Predicting stock market volatility is widely used in the management of portfolios, analysis of risk, and determination of option prices. This study is about volatility modelling of the daily Johannesburg Stock Exchange All Share Index (JSE ALSI) stock price data between 1 January 2014 and 29 December 2023. The modelling process incorporated daily log returns derived from the JSE ALSI. The following volatility models were presented for the period: sGARCH(1, 1) and fGARCH(1, 1). The models for volatility were fitted using five unique error distribution assumptions, including Student’s t, its skewed version, the generalized error and skewed generalized error distributions, and the generalized hyperbolic distribution. Based on information criteria such as Akaike, Bayesian, and Hannan–Quinn, the ARMA(0, 0)-fGARCH(1, 1) model with a skewed generalized error distribution emerged as the best fit. The chosen model revealed that the JSE ALSI prices are highly persistent with the leverage effect. JSE ALSI price volatility was notably influenced during the COVID-19 pandemic. The forecast over the next 10 days shows a rise in volatility. A comparative study was then carried out with the JSE Top 40 and the S&P500 indices. Comparison of the FTSE/JSE Top 40, S&P 500, and JSE ALLSI return indices over the COVID-19 pandemic indicated higher initial volatility in the FTSE/JSE Top 40 and S&P 500, with the JSE ALLSI following a similar trend later. The S&P 500 showed long-term reliability and high rolling returns in spite of short-run volatility, the FTSE/JSE Top 40 showed more pre-pandemic risk and volatility but reduced levels of rolling volatility after the pandemic, similar in magnitude for each index with low correlations among them. These results provide important insights for risk managers and investors navigating the South African equity market. Full article

Climate change manifests itself in rising temperatures across the continent and affects the El Niño–Southern Oscillation (ENSO) by changing sea surface temperatures and atmospheric circulation. This affects precipitation and temperature patterns, with South Africa normally experiencing drier conditions during El Niño events. These weather anomalies influence crop yields and food prices. Spatial price transmission indicates the extent to which prices of agricultural goods are linked across different geographical areas and how quickly price signals from one area are passed on to another. Although numerous studies explore spatial price transmission between various countries, there is a gap in the literature on price transmission between the US and South African maize markets during ENSO events. Therefore, we investigate how ENSO-related events impacted maize price transmission between the Chicago Mercantile Exchange and the Johannesburg Stock Exchange from 1997 to 2024. The empirical analysis starts with a correlation analysis, followed by tests for cointegration and error correction models. The results confirm the dominating impact of US maize prices on South African prices, but also how this relationship changes based on the nature of the ENSO event. There is some indication of lower levels of integration and higher levels of price diversion during El Niño periods. Full article

Integrated thinking and connectivity have recently attracted particular attention in sustainability reporting. A firm’s reporting on its Environmental, Social, and Governance (ESG) practices should be connected to the other business functions to optimize the ESG information provided through integrated reports. Academic research on the connectivity between ESG information and other business functions is limited. Hence, the main aim of this study is to analyze and characterize the reporting connectivity between the Sustainable Development Goals (SDGs) and other business functions of South African retail banks. This is done using a thematic content analysis of the integrated reports of each bank in the sample from 2016 to 2023. The sample consists of the top five retail banks in South Africa that are listed on the Johannesburg Stock Exchange (JSE). Specifically, the researchers determine the number of occurrences where the SDGs are linked to other business functions through an iterative process. Furthermore, several Analysis of Variance (ANOVA) models are implemented to identify which content elements have the strongest connectivity to the SDGs as well as to identify which elements have the strongest linkage to the various content elements. The results show that SDGs are primarily linked to stakeholders, the business model, and performance. Furthermore, it was found that this sample of South African banks most prominently links these business functions to SDG 8, which aligns with the banks’ purpose of furthering economic development. Full article

This study investigates systemic risk, return patterns, and diversification within the Johannesburg Stock Exchange (JSE) during the COVID-19 pandemic, utilizing data-centric approaches and the ARMA-GARCH vine copula-based conditional value-at-risk (CoVaR) model. By comparing three investment strategies—industry sector-based, asset risk–return plot-based, and clustering-based—this research reveals that the industrial and technology sectors show no ARCH effects and remain isolated from other sectors, indicating potential diversification opportunities. Furthermore, the analysis employs C-vine and R-vine copulas, which uncover weak tail dependence among JSE sectors. This finding suggests that significant fluctuations in one sector minimally impact others, thereby highlighting the resilience of the South African economy. Additionally, entropy measures, including Shannon and Tsallis entropy, provide insights into the dynamics and predictability of various portfolios, with results indicating higher volatility in the energy sector and certain clusters. These findings offer valuable guidance for investors and policymakers, emphasizing the need for adaptable risk management strategies, particularly during turbulent periods. Notably, the industrial sector’s low CoVaR values signal stability, encouraging risk-tolerant investors to consider increasing their exposure. In contrast, others may explore diversification and hedging strategies to mitigate risk. Interestingly, the industry sector-based portfolio demonstrates better diversification during the COVID-19 crisis than the other two data-centric portfolios. This portfolio exhibits the highest Tsallis entropy, suggesting it offers the best diversity among the types analyzed, albeit said diversity is still relatively low overall. However, the portfolios based on groups and clusters of sectors show similar levels of diversity and concentration, as indicated by their identical entropy values. Full article

Sentiment analysis is a well-known task that has been used to analyse customer feedback reviews and media headlines to detect the sentimental personality or polarisation of a given text. With the growth of social media and other online platforms, like Twitter (now branded as X), Facebook, blogs, and others, it has been used in the investment community to monitor customer feedback, reviews, and news headlines about financial institutions’ products and services to ensure business success and prioritise aspects of customer relationship management. Supervised learning algorithms have been popularly employed for this task, but the performance of these models has been compromised due to the brevity of the content and the presence of idiomatic expressions, sound imitations, and abbreviations. Additionally, the pre-training of a larger language model (PTLM) struggles to capture bidirectional contextual knowledge learnt through word dependency because the sentence-level representation fails to take broad features into account. We develop a novel structure called language feature extraction and adaptation for reviews (LFEAR), an advanced natural language model that amalgamates retrieval-augmented generation (RAG) with a conversation format for an auto-regressive fine-tuning model (ARFT). This helps to overcome the limitations of lexicon-based tools and the reliance on pre-defined sentiment lexicons, which may not fully capture the range of sentiments in natural language and address questions on various topics and tasks. LFEAR is fine-tuned on Hellopeter reviews that incorporate industry-specific contextual information retrieval to show resilience and flexibility for various tasks, including analysing sentiments in reviews of restaurants, movies, politics, and financial products. The proposed model achieved an average precision score of 98.45%, answer correctness of 93.85%, and context precision of 97.69% based on Retrieval-Augmented Generation Assessment (RAGAS) metrics. The LFEAR model is effective in conducting sentiment analysis across various domains due to its adaptability and scalable inference mechanism. It considers unique language characteristics and patterns in specific domains to ensure accurate sentiment annotation. This is particularly beneficial for individuals in the financial sector, such as investors and institutions, including those listed on the Johannesburg Stock Exchange (JSE), which is the primary stock exchange in South Africa and plays a significant role in the country’s financial market. Future initiatives will focus on incorporating a wider range of data sources and improving the system’s ability to express nuanced sentiments effectively, enhancing its usefulness in diverse real-world scenarios. Full article

This study examined the connectedness and propagation of risk in the South African equity sectors during the Global Financial Crisis (GFC), the European Debt Crisis (EDC), the US–China trade war, and the COVID-19 pandemic. Daily returns of nine Johannesburg Stock Exchange (JSE) super sectors were examined from 3 January 2006 to 31 December 2021. Applying the connectedness matrix and time-varying parameter vector autoregressive (TVP-VAR) model, in full sample and sub-periods, the study showed that dynamic total connectedness of the super sectors is high in absolute form (62%). Furthermore, it was found that the highest volatility connectedness was during the EDC (68.83%) and during the COVID-19 pandemic (68.57%), followed by the GFC (63.16%) and lastly the US–China trade war (42.09%), respectively. This suggests that the tendency for a systemic risk is highest during the EDC, COVID-19, and GFC periods, and lowest during the US–China trade war. The financial sector was the primary net-transmitter of shocks during the COVID-19 period, while the automobile and parts sector was the strongest net-transmitter of shocks during the GFC, EDC, and US–China trade war. Similarly, the strongest net recipient of shocks during GFC, EDC, and COVID-19 is the chemical super sector. The study concludes that there is a significant volatility connectedness among JSE super sectors. In addition, the JSE super sectors exhibit time-varying connectedness during extreme events. Moreover, the net-transmitter and net-receiver of shock do not change significantly during different crisis periods. The policy implications of the findings are highlighted in the concluding section. Full article

In this paper, the use of artificial neural networks (ANNs) is proposed to approximate the option price sensitivities of Johannesburg Stock Exchange (JSE) Top 40 European call options in a classical and a modern multi-curve framework. The ANNs were trained on artificially generated option price data given the illiquid nature of the South African market, and the out-of-sample performance of the optimized ANNs was evaluated using an implied volatility surface constructed from published volatility skews. The results from this paper show that ANNs trained on artificially generated input data are able to accurately approximate the explicit solutions to the respective option price sensitivities of both a classical and a modern multi-curve framework in a real-world out-of-sample application to the South African market. Full article

The supply chain leadership (SCL) concept has gradually gained traction among various stakeholders such as legislators and specialists because of its dependable practices for companies in sustainable innovation and competitiveness across developing economies. The effective implementation of SCL strategic actions in a company can initiate sustainable innovation and competitiveness at each level of the company. Statistical data collection was performed for 46 of the top 100 Johannesburg Stock Exchange (JSE)-listed companies through an online Survey Monkey questionnaire. The primary purpose of this study was to identify the SCL strategic actions that are undertaken by companies in a developing economy regarding sustainable innovation and competitiveness. The findings significantly reveal empirical insights for companies to include and leverage in SCL strategic actions that influence sustainable innovation and competitiveness in an emerging economy. The findings show that firms operating within developing economies must adopt, and recognize the importance of, sustainable innovation and competitiveness in their practices for the betterment of the goods and services provided to the market. A major contribution is offered to the literature for the assistance and planning of sustainable innovation and competitive practice in developing economies in a global environment. This study further offers a robust recognition of, and information about, the characteristics and strategies that commonly lead to SCL being prioritised by the top 100 JSE-listed companies. Full article

Financial market data are abundant with outliers, and the search for an appropriate extreme value theory (EVT) approach to apply is an endless debate in the statistics of extremes research. This paper uses EVT methods to model the five-year daily all-share total return index (ALSTRI) and the daily United States dollar (USD) against the South African rand (ZAR) exchange rate of the Johannesburg stock exchange (JSE). The study compares the block maxima approach and the peaks-over-threshold (POT) approach in terms of their ability to model financial market data. The 100-year return levels for the block maxima approach were found to be almost equal to the maximum observations of the financial markets of 10,860 and R18.99 for the ALSTRI and the USD–ZAR, respectively. For the peaks-over-threshold (POT) approach, the results show that the ALSTRI and the USD–ZAR exchange rate will surpass 17,501.63 and R23.72, respectively, at least once in 100 years. The findings in this study reveal a clear distinction between block maxima and POT return level estimates. The POT approach return level estimates were comparably higher than the block maxima estimates. The study further revealed that the blended generalised extreme value (bGEVD) is more suitable for relatively short-term forecasting, since it cuts off at the 50-year return level. Therefore, this study will add value to the literature and knowledge of statistics and econometrics. In the future, more studies on bGEVD, vine copulas, and the r-largest-order bGEVD can be conducted in the financial markets. Full article

This paper examines the effects of the Standard and Poor’s 500 (SP500) stock index crash during the global financial crisis and the COVID-19 pandemic periods on the South African top sector indices (basic materials, consumer goods, consumer services, financials, healthcare, industrials, technology, and telecommunication). The results of a copula-based BEKK-GARCH approach technique demonstrate the existence of price and volatility spillover during times of stock crashes. We discover that during a stock crisis, strong shocks and higher volatility spillover effects from the United States (U.S.) SP500 index to the top sector indices of the South African Johannesburg Stock Exchange (JSE) markets are more significant. However, there is no integrated economy, as the results did not show any spillover effects from South Africa to U.S. markets. Furthermore, the Gumbel copulas have higher dependence parameters, implying that extreme co-movements occur in the upper tails, suggesting the possibility of a large transmission of shocks from the SP500 to the eight top sector indices of the JSE and showing an asymmetric dependence between these markets. This result is important for investors willing to invest in the South African sector of equity markets to develop hedging strategies to prevent risk spillover from developed markets. Full article