Faculty of Accounting and Informatics
Permanent URI for this communityhttp://ir-dev.dut.ac.za/handle/10321/1
Browse
123 results
Search Results
Item Integration of an autoencoder model with an actor-oriented system(Advances in Artificial Intelligence and Machine Learning, 2024) Dyubele, Sithembiso; Cele, Noxolo Pretty; Mbangata, LubabaloTraditional machine learning frameworks often struggle with scalability, modularity, and efficient resource management, especially when dealing with vast data. Actor-Oriented Systems offer a robust framework for building such scalable systems, allowing concurrent processing and efficient handling of large datasets. This study investigated the integration of Autoencoders (AE), which are pivotal in unsupervised learning, with Actor-Oriented Systems to enhance the modularity, scalability, and maintainability of the model training process. The study seeks to leverage the capabilities of AE and Actor-Oriented Systems to achieve high-quality image reconstruction and efficient processing. The study also attempted to understand the underlying patterns in the data, assess the performance of the model, and demonstrate the benefits of modular and scalable systems. Key findings from the results showed significant improvements in training efficiency and performance of the model, especially when using Actor-Oriented Systems. The training time was reduced from 16.96 seconds to 14.21 seconds, and the validation loss improved from 0.2768 to 0.2100, indicating better generalisation and learning. Data augmentation techniques further enhanced the robustness of the model, leading to more accurate reconstructions of the test images. Actor-Oriented Systems facilitated concurrent processing, improved modularity, and enabled the system to scale efficiently with increasing data volume. This study also highlighted the practical benefits of integrating AE with Actor-Oriented Systems, providing valuable insights into building more robust, maintainable, and scalable machine learning workflows.Item A review of artificial intelligence implementation in academic library services(Stellenbosch University, 2024-08-28) Zondi, Nombuso Phamela; Epizitone, Ayogeboh; Nkomo, Ntando; Mthalane, Peggy Pinky; Moyane, Smangele; Luthuli, Mthokozisi; Khumalo, Mbalenhle; Phokoye, SamkelisiweArtificial intelligence (AI) has emerged as a transformative force across various sectors, including academic libraries, offering potential paradigm shifts in operations and patron services. The imperative need for AI in educational library services stems from its myriad advantages in enhancing efficiency and service quality. Despite its promise, the integration of AI within academic libraries faces hurdles such as expertise shortages, infrastructure limitations, financial constraints, and employment concerns. This paper critically seeks to assess AI implementation in academic library services. The aim is to uncover adoption drivers and challenges in AI implementation in academic libraries. This paper conducts a comprehensive literature review to explore implementation of AI in academic libraries. The findings of the study indicate that AI implementation heralds an era of enhanced service delivery, albeit accompanied by challenges, notably in developing countries like South Africa. It also indicates that success hinges on meticulous planning, collaborative teamwork, adequate funding, and proactive promotion. Furthermore, the paper’s findings offer librarians and top management insights into navigating the adoption of AI projects within academic library settings efficiently.Item The impact of financial statement quality and firm characteristics on access to finance by small and medium-sized enterprises in eThekwini(2024) Mayendisa, Qiniso Prince; Stainbank, Lesley June; Ramsarghey, AnchalThe South African government has established several public sector institutions that cater to small and medium-sized entities’ (SMEs) needs through the Department of Trade, Industries and Competition. These institutions, known as Business Development Service Providers, assist SMEs in running their businesses more effectively and can enhance access to finance as an alternative form of collateral in circumstances where security for a loan is required. However, most SMEs apply for finance from financial institutions. As access to finance has been identified as a major obstacle limiting the growth and survival of SMEs, the objective of this research was to investigate the impact of financial statement quality and firm characteristics on access to finance by SMEs in eThekwini using the “Applied and Received” approach. The main research objective was divided into three sub-objectives; these were to determine the forms of finance being used by SMEs, to determine the accounting frameworks being used by SMEs, and to investigate whether financial statement quality and firm characteristics affect their access to finance. To achieve these objectives, a questionnaire was administered to owners of SMEs in eThekwini. The results revealed that the main forms of finance used by the SMEs were overdraft facilities, bank loans, factoring, leasing, and hire purchase, and that the average rate of extent of access to finance is 19.10%. The findings also revealed that 4.8% of the respondents were using IFRS, 72.9% were using IFRS for SMEs, and 22.3% were using South African Statements of Generally Accepted Accounting Practice. Lastly, the findings revealed that firm age, firm size, collateral, and financial statement quality have a significant effect on access to finance by SMEs. Therefore, possession of such firm characteristics and financial statement quality are important predictors of SMEs’ successful access to finance. The Government needs to help SMEs by providing them with educational programs that will assist them in compiling and understanding their financial statements to keep them improving and surviving. Furthermore, an SME’s growth and survival also depends on its access to finance.Item Data mining and machine learning : a study of the CO2 emission trends in South Africa(2024) Mohamed, Ghulam Masudh; Patel, Sulaiman Saleem; Naicker, NalindrenThis study addresses the pressing global issue of elevated carbon dioxide emissions (CO2E), with a particular focus on South Africa (SA), which ranks amongst the world's top emitters and largest in Africa. By introducing a novel integration of Change-point Analysis (CPA) and Machine Learning (ML) techniques, this research addresses significant gaps in CO2E trend analysis. Unlike previous studies, this research applies CPA methodologies within the distinct context of SA, employing algorithms like cumulative sum (CUSUM) and Bootstrap analysis to pinpoint crucial change-points in CO2E data specific to the country. The Bootstrap analysis determines the confidence levels associated with each detected change. Additionally, this study sought to validate historical trends and predict future patterns using ML models, with a specific focus on employing the AdaBoost ensemble learning technique. Drawing on insights from a Preferred Reporting Items for Systematic Reviews and MetaAnalyses (PRISMA)-based systematic review, the research selects input variables based on the factors identified as significant contributors to CO2E, ensuring the models capture the relevant variables effectively. The results of the systematic review highlight energy production and economic growth as key drivers of CO2E, thus validating their selection as input data for constructing the CPA and ML models. To conduct this study, secondary data was obtained from the World Bank's Open Data initiative data repository, a common source for environmental research. This selection was justified by a literature review, which highlighted the reliability and applicability of this data source. The CPA results reveal significant change-points in electricity generation, economic growth, and CO2E, with an average confidence level of 94%, indicating the accuracy of this analytical approach. Moreover, the CPA results emphasise the relationship between economic growth, electricity production, and CO2E in SA. Before forecasting future CO2E trends, the effectiveness of the AdaBoost regressor in enhancing model performance was benchmarked against traditional ML algorithms, including Linear regression, Polynomial regression, Bayesian Linear regression and K-Nearest Neighbors (KNN) regression, to determine the most effective technique for forecasting CO2E. The researcher evaluated model performance using key regression ML performance metrics, including Root Mean Squared Error (RMSE), Mean Absolute Error (MAE), coefficient of determination (R2) score, and an additional accuracy score introduced by the researcher. Notably, the AdaBoost models demonstrated superior performance, with an average RMSE score of 10,143.17 kilotons (kt), MAE score of 9,642.64 kt, R2 of 0.90, and accuracy of 96.74%. The study also revealed that, on average, models that were trained using the AdaBoost algorithm surpassed traditional ML models, in terms of performance. They achieved a reduction in RMSE score by 6,417.29 kt, a decrease in MAE score by 4,358.09 kt, an increase in R2 score by 0.07 and enhanced accuracy by 0.60%. Additionally, a comparative analysis of the repeated holdout methods and cross-validation techniques was conducted, with results revealing that repeated holdout had a more significant impact on model performance. After excluding outliers, the average improvement in crossvalidation results, due to the repeated holdout method, was a decrease of 783.32 kt for RMSE, a reduction of 1,289.39 kt for MAE, and an increase of 0.88% for accuracy. The extent to which the repeated holdout method improved the performance of ML models that were integrated with cross-validation techniques, was correlated with the initial model performance. For ML models with RMSE and MAE scores equal to or exceeding 15,000 kt, the findings indicate that the repeated holdout methods studied should enhance performance by at least 2,000 kt. Similarly, an improvement of nearly 3% or higher in accuracy was noted, when the crossvalidation value for this metric was 94% or lower. The AdaBoost model, integrated with repeated holdout, was selected as the optimal model, as evidenced by the results, for forecasting CO2E in SA from 2021 to 2027. The forecasted CO2E trends validate that energy production and economic growth are indeed the primary drivers of CO2E in SA, as previously highlighted by the CPA model. This underscores the importance of addressing these factors to effectively mitigate carbon emissions in the country. Moreover, the forecasted results indicate that SA is unlikely to meet the global temperature limit of 1.5 degrees Celsius by 2030, given the trajectory showing a shortfall in achieving the target level of 334 million tonnes (Mt) of CO2E, agreed upon in the Paris Agreement. However, the country did meet its CO2E commitments outlined in the 2030 National Development Plan, showing some progress towards environmental sustainability. Nonetheless, the failure to meet these targets at their lower ranges suggests the need for further efforts to reduce carbon emissions, which is crucial for aligning with the Paris Agreement objectives and achieving a zero net emission rate by 2050. This highlights the importance of ongoing initiatives to enhance environmental policies and practices in SA. Future research should focus on integrating load-shedding dynamics into the analysis to examine and confirm its effects on energy production, economic growth, and CO2E in SA. Additionally, future research should focus on forecasting future change-points for the socio-economic indicators or variables utilised in this study. This can help policymakers anticipate fluctuations and devise proactive strategies, to address environmental and economic challenges effectively. It is also recommended that future research consider the output of renewable energy production, when analysing CO2E trends.Item Health insurance cross-selling predictions with machine learning for South African consumers(2024) Mavundla, Khulekani; Thakur, SurendraCross-selling is the practice of selling additional products or services to an existing customer to increase business revenue. Cross-selling health insurance is challenging for companies, as they spend significant time meeting with prospective clients without knowing the likelihood of a sale. A health insurance provider often markets additional insurance products to its clients through different channels. This study aims to develop a robust ML model to help health insurance companies identify potential customers likely to engage in cross-selling. Objectives include extracting and preparing customer data from a large South African insurance company using suitable ML techniques. The study also seeks to determine effective algorithms for predicting health insurance cross-selling and to identify influential features for algorithm selection. This study adopted a quantitative research approach focused on extracting health insurance customer data. To achieve this, the study applied ML techniques by using the Python language using a dataset obtained from a large South African insurance company which is a rich repository that contains demographics, health conditions, and policy information. The study applied various ML algorithms, including Random Forest, KNearest Neighbors, XGBoost classifier, and Logistic Regression, feature engineering techniques were employed to enhance predictive accuracy. Analyzing 1,000,000 customer records with 17 features, Random Forest emerged as the top model with an accuracy of 0.91 and an F1 score of 1.00. The study found that customers aged 2570, with prior insurance and longer service history, are more likely to purchase additional health insurance. This study will assist insurance providers in developing a strategy for reaching out to those clients in order to enhance their business operations and revenue.Item Determinants of participation of Msunduzi local municipality’s peri-urban households in the digital finance economy(2024) Nyide, Nelisiwe Fortunate; Olarewaju, Odunayo MagretDigital finance is an instrument that has the potential of improving access to finance to underprivileged groups such as peri-urban communities. Digital financial tools are capable of achieving traditional crisis management objectives with greater potency and accuracy than was historically possible. The financial services sector is in a process of accelerating change by adopting new business models based on convergent technological developments to increase customer participation in periurban areas. Therefore, the financial services sector can use digital finance to improve the availability of household financial services through diversified financial products, thus promoting the growth of household consumption. However, several studies maintain that determinants of digital finance participation of marginalised households, including peri-urban households, are generally underdetermined. Moreover, there is limited literature on the participation of South African households in the digital economy. Scholarly literature asserts that the level of participation of South Africans in digital finance is concerning. This is largely due to a lack of awareness and knowledge of digital financial services that are available to South African households. This study seeks to bridge that gap by examining the determinants of participation of peri-urban households in digital finance in the financial services sector in KwaZuluNatal, South Africa. A quantitative research approach was adopted to answer the research questions. This method was found to be suitable for this study given that the research objectives can be best measured using a structured survey that is quantitative in nature. The target population of this study consisted of peri-urban households located in the Greater Edendale area, which is the largest peri-urban area within the Msunduzi Local Municipality. The sample size for this study was 384 periurban households which were selected using purposive sampling, derived from nonprobability sampling. The questionnaires were in English and were also translated into isiZulu in order to make it easier for respondents to participate in this study. The Statistical Package for the Social Sciences (SPSS) was used to compile the descriptive statistics. The results of this study indicate that the general public in economically disadvantaged communities participates in digital financial transactions in the financial services sector on a regular basis. A Spearman correlation analysis found a substantial positive link between the usage of digital platforms by peri-urban families and their degree of participation in digital finance. This association was shown to be statistically significant (r = .649, n = 315, p < .001). However, the results of a Mann-Whitney U test showed that there was no statistically significant difference between genders with regard to involvement in digital finance (Z = -1.804, p = .071). A correlation analysis was undertaken to determine whether peri-urban households’ awareness of digital financial services influenced their adoption of digital platforms. The Spearman correlation analysis (r = .768, n = 315, p < .001) showed a strong and significant relationship between peri-urban households’ knowledge and awareness of digital financial services and their use of digital platforms. Additionally, a Spearman correlation analysis (r = -.524, n = 315, p < .001) revealed a significant negative association between peri-urban households’ adoption of digital financial platforms and their digital literacy. This is despite the fact that literature argues that in South Africa, the adoption of digital financial services is negatively affected by a lack of information and knowledge which is prevalent among marginalised communities.Item Evolving a framework to observe and analyse customer experience on the Twitter platform using machine learning techniques(2024) Moodley, Thaneshni; Thakur, SurendraRetailers have become more focused on retaining and turning existing customers into longterm clients because retailers have become more competitive, customers more demanding, and competitors more aggressive. The 2020 COVID-19 pandemic has forced a transformation for retailers. Within months, a revolution has taken place, constituting major changes to how consumers view cash, how they shop online and what they expect from retailers as part of a positive buying experience. Consumers increasingly expect retailers to create a seamless customer experience. This often means leaning on digital capabilities to create a seamless, omni-channel experience by linking different aspects of the customer shopping experience. The usage of big data analytics has primarily been implemented outside of South Africa to better understand customer connections and experiences, highlighting a noticeable research gap in South Africa. It has been proven to be an effective tool for retailers in predicting customer behaviour. There is a need to reduce the complexities in understanding which are the most appropriate machine learning techniques for sentiment analysis of online customer experience and to capitalise on development. Thereafter, online retailers are better equipped to tailor machine learning tools to craft analytical tools. Given the massive migration to online transactions, this work presents a rigorous analysis of social media posts, which is paramount for modern-era retailers. Businesses can use sentiment analysis to determine how well their brand is performing in the marketplace, learn more about the attitudes of their customers and determine whether their items receive more positive or negative feedback. A longitudinal study was adopted to analyse a dataset of retail-related tweets for the identification of customer complaints using a sentiment analysis hybrid approach, which is a combination of lexicon and machine learning approaches. A conceptual framework was developed to observe and analyse customer experiences on the Twitter platform using machine learning techniques. The framework encompasses components such as data preparation, natural language processing pre-processing techniques, calculating sentiment using sentiment lexicon and ML techniques, and thereafter a selection of the best-performing machine learning technique for sentiment analysis within the developed conceptual framework. The extracted dataset contains 240 000 tweets posted between 01 January 2017 and 31 January 2019, out of which 27 233 tweets were selected for the study. Natural language pre-processing techniques were applied to the dataset, including tokenisation, stemming, lemmatisation, part-of-speech tagging, and name-of-entity recognition. Supervised and deep machine learning gave the best results of 61.75 and 60.25. This study has identified deep learning as a good technique for sentiment analysis when NLP pre-processing methods are done in a certain order. A study on analysing retail complaints posted on the Twitter platform using a sentiment analytic framework has not been done in South Africa before. This study has proven that the sentiment analysis hybrid approach is highly capable of analysing social media data.Item The inclination to pursue fashion and beauty digital entrepreneurship amongst selected final year Diploma students in a South African university(2024) Maphanga, Ezile; Moyane, Smangele Pretty; Nkomo, NtandoIn the age of digital transformation, the inclination to pursue digital entrepreneurship has become rampant, bringing about a broader acceptance of the idea of conducting business online especially by young people. In that regard, entrepreneurs are seizing the opportunity through digital entrepreneurship, with the fashion and beauty industry being a prominent sector for online business. Despite the growth in online fashion and beauty trading, there is limited research and understanding with the discourse surrounding it. The aim of the study was to examine the inclination to pursue fashion and beauty digital entrepreneurship amongst selected final year Diploma students in a South African university. The objectives of the study were: to establish the level of interest in pursuing digital entrepreneurship with regards to fashion and beauty amongst selected final year Diploma students, to determine factors that would influence the uptake of digital entrepreneurship with reference to fashion and beauty amongst selected final year Diploma students, and to assess using the Technology Acceptance Model (TAM) the inclination to pursue digital entrepreneurship in fashion and beauty amongst selected final year Diploma students. The study employed the Technology Acceptance Model to determine whether students intended to accept digital entrepreneurship. Methodologically, the study implemented the positivist research paradigm. The research approach chosen was quantitative. A survey research design was conducted through a questionnaire, as a data collection tool, from a census of the 29 final year students studying their Diploma in Fashion Design and 65 studying for their Diploma in Somatology. Instruments were pre-tested on 10 students, 5 in the Advanced Diploma in Fashion Design and 5 in the Advanced Diploma in Somatology at DUT. Findings showed a strong interest to pursue digital entrepreneurship in the fashion and beauty space. However, hesitations related to ‘customer satisfaction’ and ‘trust’ negatively influence the uptake of digital entrepreneurship. The findings also revealed that respondents were most likely to incorporate digital technologies in their businesses and saw the importance of administrative functions and advertising skills to have when venturing into digital entrepreneurship. The study recommends the youth to: be encouraged to consider entrepreneurship by South African universities; familiarize themselves with digital entrepreneurship and get education and knowledge in that regard; acquire the necessary skills in order to venture into digital entrepreneurship.Item Bio-inspired optimisation of a new cost model for minimising labour costs in computer networking infrastructure(2024) Nketsiah, Richard Nana; Millham, Richard Charles; Agbehadji, Israel EdemThis thesis revolves around the bio-inspired optimisation of a newly formulated cost model tailored for initial installation of a user-specified computer networking infrastructure, motivated by requirements of networking industries, with a focal point on minimising labour costs. The new cost function of this infrastructure installation incorporates essential decision variables related to labour, encompassing the daily requirements and costs of both skilled and unskilled workers, their respective hourly rates, installation hours, and the overall project duration. This deliberate emphasis on labour-centric factors aim to offer nuanced insights into the intricacies of project budgeting and resource allocation. The research critically evaluates the effectiveness of the cost function by examining various factors, such as daily fixed costs, a size and complexity factor tailored to individual scenarios, and a penalty coefficient aimed at ensuring compliance with project schedules. Significantly, the deliberate exclusion of equipment, material, maintenance and operational costs underscores the focused examination of labour-related expenditures, providing a unique contribution to the optimisation landscape within the installation of the user-specified computer networking infrastructure projects. Utilising advanced bio-inspired optimisation techniques, alongside real-world data, this study endeavours to gauge the effectiveness of the new cost model in minimising labour expenses while upholding optimal network performance. The anticipated outcomes of this study extend beyond theoretical contexts to practical implications, providing actionable insights and recommendations for network infrastructure planners. The significance of labour-centric considerations in project planning and design is underscored, providing a more encompassing perspective that aligns with the evolving landscape of modern technological infrastructures. By giving attention to labour-intensive aspects within installation of computer networking infrastructure projects, the thesis aspires to enhance budgeting accuracy and streamline resource allocation processes, thereby fostering more efficient and cost-effective project outcomes.Item Evaluating the level of satisfaction in higher education students with technical support services provided using fuzzy TOPSIS decision method(2024) Pursan, Geeta; Adeliyi, Timothy T.; Joseph, SeenaThe use of information and communication technologies at higher education institutions is no longer an option, but rather a need. Information Technology support is an essential factor that entails giving end users assistance with hardware and software components. Technical support for information technology has been recognized as a crucial element linked to student satisfaction because it helps students understand, access, and use technology efficiently. IT technical support services are essential for higher education students to succeed in their studies. However, the quality of IT technical support services can vary widely from institution to institution. Student satisfaction with IT technical support services is an important measure of the quality of education that students receive. Conversely, evaluating student satisfaction is a complex task, as it involves subjective assessments of service quality. This dissertation used a framework that combines three approaches: Principal Component Analysis (PCA), Service Quality (SERVQUAL), and Fuzzy TOPSIS. The successful implementation of IT technical support is aided by identifying the essential success criteria that enable efficient and effective support for students and instructors. Hence the main aim of this study is to identify and rank the key success factors for the successful implementation of IT technical support at higher education institutes. 81 key success factors identified from 100 research papers were analyzed using principal component analysis. The findings led to the identification and ranking of 25 PCs. From these findings, the SERVQUAL dimensions that featured at the top-most rankings were selected, and that being: tangibility, reliability, assurance, empathy, and responsiveness. These factors were used in the development of the questionnaire that was sent to students which measured student perceptions of the five dimensions of service quality. The proposed approach is implemented in a higher education institution in South Africa. The questionnaires were administered to a specific target of students, only those student participants’ who had contacted the IT technical team for IT technical support via the WhatsApp service communication method formed part of the study. Once data was collected, SERVQUAL which is a well-established scale for measuring service quality was used to calculate the average score for each dimension of service quality. The dimensions of service quality where students were most and least satisfied were identified. Finally, Fuzzy TOPSIS, which is a multi-criteria decisionmaking (MCDM) method that handles uncertainty and vagueness in data was used to rank the IT technical support services based on student satisfaction. The SERVQUAL results showed that the overall satisfaction level of students with IT technical support services led to a final score of 60 percent, meaning that the support services rendered were acceptable to students. The Fuzzy TOPSIS rankings identified the sub-criteria, overall being satisfied with the support services rendered as rank number one. As can be deduced that since both the SERVQUAL and Fuzzy TOPSIS methods have nominated satisfaction level as the common factor, this research indicates that the IT technical support services rendered by the IT technical support team are adequately sufficient and that the needs of the students are met and that the services rendered are highly appreciated by the students at the Durban University of Technology. This research proves that the IT support team is compliant with the quality of IT technical support services rendered to students at the Durban University of Technology however, the IT support service can be improved by the proactiveness of the technical team. This research contributes by providing useful information highlighting factors that can be used to examine areas in educational institutions that need to receive continuous and special care to generate high student satisfaction; ensure future success and gain a competitive advantage. These factors can assist the management of HEI in determining the success or failure of an institution in terms of the technical support provided to students and student satisfaction. The results of this evaluation can be used by other HEIs to improve the quality of IT technical support services and to ensure that they are meeting the needs of students.