Masters Degrees (Industrial Engineering)

Permanent URI for this collection

https://scholar2.stb.sun.ac.za/handle/10019.1/776

Browse

Recent Submissions

Now showing 1 - 5 of 417
  • Thumbnail Image
    Item
    Reinforcement learning for algorithmic day trading on the Johannesburg Stock Exchange
    (Stellenbosch : Stellenbosch University, 2023-02) Richards, Nicole; Eldon, Burger; Thorsten, Schmidt-Dumont; Stellenbosch University. Faculty of Engineering. Dept. of Industrial Engineering.
    ENGLISH ABSTRACT: Given the rapidly advancing capabilities of modern computers, there has been a considerable increase in interest in algorithmic trading. From reducing trading latency by purchasing highly sought-after property as close to stock exchanges as possible, to conducting research on the capabilities of the most recent artificial intelligence algorithms on the stock markets, market participants and academic researchers are all looking for innovative methods to achieve maximum returns with minimum risk. In this thesis, a reinforcement learning approach is adopted to determine the capabilities of such algorithms, along with a suitable neural network architecture, to make day trading decisions. A reinforcement learning agent learns through a process of trial-and-error. The agent performs various actions in order to determine which actions yield rewards, which reinforce desirable behaviour. The capacity of reinforcement learning algorithms to improve their decision-making over time through self-learning makes them naturally suitable for algorithmic trading. During the experiments conducted for this thesis, the reinforcement learning agents were trained and tested on the Johannesburg Stock Exchange. A day trading approach is taken, which means positions are never kept overnight, in an e ort to reduce trading risk. Furthermore, the available computational power is proposed as a limiting factor to determine the capabilities of such a reinforcement learning trading approach in a personal capacity when no special computational facilities are available. Various experiments are conducted to determine the impact of di erent reward functions, neural network architectures, and reinforcement learning algorithms on the reinforcement learning agents' day trading performance in terms of pro tability and risk. Additionally, hyperparameter optimisation is performed, which yields improved performance across all reinforcement learning agents. Certain inputs and reward functions are better suited to the default reinforcement learning algorithm parameters, and hyperparameter optimisation of the reinforcement learning algorithm parameters is required to make fair comparisons between the di erent reward functions and algorithms. When the number of stocks available on the Johannesburg Stock Exchange environment is increased, the nal account value that the reinforcement learning agent achieved also increased. The computational power limited the number of stocks that could be available within the Johannesburg Stock Exchange environment, but the results of this thesis serve as a proof-of-concept of reinforcement learning for algorithmic trading on the Johannesburg Stock Exchange.
  • Thumbnail Image
    Item
    Development of a peer-to-peer voucher donation management system enabled by blockchain
    (Stellenbosch : Stellenbosch University, 2023-02) Harraway, Tricia Margaret; Bekker, James; Stellenbosch University. Faculty of Engineering. Dept. of Industrial Engineering.
    ENGLISH ABSTRACT: In recent years charity and philanthropy sectors have experienced a surge in the availability of digital resources to aid in providing transparency in their operations and donation processing. There is no doubt that the world is transitioning into a digital space, where new solutions to existing problems could be approached with emerging technology. The Payments Association of South Africa (PASA) is aiming for a cashless society by 2030. Two frequently cited barriers to financial inclusion and bank account ownership is distrust in the system and lack of formal identification. As a result, FinTech companies are playing a larger role in providing innovative solutions for the undocumented and unbanked population, using technologies such as blockchain. Africa has a rich history of community philanthropy where horizontal giving is likely to be in the form of micro-donations such as cash, food or clothing. If fewer individuals rely on paper notes and coins, the concern is that those informal peer-to-peer donations will become less frequent and more challenging to make. Vouchers have been used in the past, in order to ensure donations are spent responsibly. In addition, e-vouchers provide higher levels of security, the possibility for different donation platforms to be digitally integrated and adapted, and as well as improved levels of engagement in the donation process. Programmable vouchers have all these benefits and also the potential to enable direct and customised donor-to-beneficiary charitable payments, without the need for trusted third party service providers. The potential for a digital, transparent peer-to-peer mechanism to donate vouchers in the form of blockchain tokens is presented. Blockchain technology enables distributed networks of trust, where instead of relying on a central entity, trust is shared among peers. Furthermore, the level of transparency presented by blockchain enables traceability of the movements of the donations. By disintermediating the process of supporting peers, providing transparency in resource allocation and increasing transaction efficiency, blockchain provides a use-case for decentralised, horizontal and direct ‘giving’. This research project explores the development of a digital voucher donation mechanism where the shortcomings of traditional voucher management systems, such as requiring a bank account or mobile device or needing formal identification on request, are challenged. To address these challenges and the need for financial inclusion, existing voucher transfer architectures and humanitarian information systems were consulted and a demonstrator was developed. A decentralised application with a front-end is designed and developed to interface with the smart contracts that hold the logic of the voucher donation management system. Vouchers are minted as tokens on the Polygon network to present scalability in the future. Traditionally the voucher transaction information was stored in a centralised database, instead they are transparently recorded on a distributed network. The blockchain acts as the back-end supporting the smart contract implementation which is deployed with predefined conditions mirroring traditional escrow services. Digital wallets are integrated, allowing beneficiaries to store and redeem their voucher tokens at participating vendors via a QR code public address. The smart contracts are verified and validated using various software tests, to ensure that their functionality fulfills the requirements of the research project. The evaluation of the demonstrator showed that blockchain technology, while still in its infancy, has the potential to empower the underserved, while providing full transparency for the stakeholders involved.
  • Thumbnail Image
    Item
    Innovation for inclusive development: an agent-based and system dynamics modelling approach to technology adoption in marginalised communities.
    (Stellenbosch : Stellenbosch University, 2023-03) Venter, Michal Barend; Grobbelaar, Sara
    ENGLISH ABSTRACT: Innovation has been described as a key driver of economic growth. Traditional forms of innovation, however, generally focus on macro-level economic growth and often fail to include marginalised communities. This has been argued to exacerbate inequality within society. The concept of Innovation for Inclusive Development (I4ID) builds on the innovation systems literature and aims to address the shortcomings of traditional innovation systems towards marginalised communities. I4ID aims to improve the socio-economic status of marginalised communities by involving them in the innovation process. The literature on I4ID has matured over recent years, but formal modelling has thus far lagged the theoretical advancements. This thesis aims to address this gap by developing a formal model of a project that introduces an innovation to a marginalised community using the I4ID literature. The conceptual foundation of the formal model was formed by combining various technology adoption models to ensure the requirements of I4ID were met. Roger’s Diffusion of Innovation (DOI) theory was used as a basis for the conceptual model. A key component of the DOI is the innovation-decision process which details various stages an individual progresses through over time as they make their adoption decision. These stages are qualitatively described in the DOI. The Decomposed-Theory of Planned Behaviour (DTPB) was incorporated to quantify the innovation-decision process with thresholds of an individual's specific belief structures (as described in the DTPB). Further, the Concerns-Based Adoption Model was incorporated to focus the innovation-decision process detailed in the DOI on the local needs and demands of the marginalised community. Finally, a hybrid-model, using system dynamics and agent-based modelling, was selected as an appropriate modelling technique to capture the macro-level system processes and the micro-level analysis of actors in a marginalised community. The developed model, the Technology Adoption Model for Marginalised Communities (TAMMAC), is intended to provide a quantitative method of identifying the critical leverage points to ensure an innovation is successfully introduced to a marginalised community. The Creation of Legitimacy function was selected to indicate whether adoption occurred successfully. This decision meant that adoption was not considered as the mere use of an innovation but rather as the positive and meaningful impact of an innovation through its use and integration within a community. Adopting this legitimacy perspective aligns with the I4ID goal of improving the socio-economic status of marginalised communities. A formal model was developed to apply the TAMMAC to the ICT for Education (ICT4E) case study. The ICT4E project aimed to improve teaching and learning in rural schools by introducing tablets. The developed model indicated that the project’s initial implementation did not foster enough legitimacy in the tablets to ensure a sustainable outcome. Several scenarios were developed to identify effective interventions to ensure the legitimization of the tablets. The key interventions identified centred around ensuring technology availability and restructuring the training offered. The TAMMAC answered calls from researchers to modify existing adoption models to be more suited for an I4ID context. Integrating system dynamics and agent-based modelling allows for a macro-level analysis of larger processes in a system and a micro-level analysis of the marginalised community. Interventions that promote the legitimacy of an innovation may be determined by analysing the decomposed belief structures of the community. However, it is recommended that future research explores ways to strengthen the measure of legitimacy in the TAMMAC and incorporate the influence of an individual’s innovativeness on their adoption-decision process.
  • Thumbnail Image
    Item
    A framework for quantifying the sensitivity of throughput rates in the South African education sector
    (Stellenbosch : Stellenbosch University, 2023-02) Reed, Edwin; Van Vuuren, Prof Jan-Harm; Stellenbosch University. Faculty of Engineering. Dept. of Industrial Engineering.
    ENGLISH ABSTRACT: Since the demise of the Apartheid era, South Africa has been grappling to restore the equality imbalance left in its wake. Education has been at the forefront of this rebuilding process, due to its proven direct relation to labour-market improvement prospects. No significant improvements in the national school education system have, however, been observed during the last twenty years. This is concerning, as studies suggest that inadequate education drives an intergenerational cycle of poverty in which children inherit the social standing of their parents or caregivers, irrespective of their own abilities or effort. The ineffectiveness of former attempts to improve educational outcomes has given rise to the following question: At what level would interventions aimed at increased pass rates in the national education system yield the most significant impact in terms of overall throughput? A review of the literature related to historical educational success rates suggests several shortcomings and difficulties that may impede a holistic examination of throughput rates in the South African education system and its role as a source of human resource capital for the country’s workforce. A significant impediment is the segregated nature of available data pertaining to the South African education system noted by the author during an attempt to analyse this system meticulously. In this thesis, a novel generic framework is proposed for modelling the progression of learners and students through the South African education system, as well as the eventual absorption of these individuals into the workforce of the country. The objective of the framework is to unify the available statistics related to education performance rates of every education sector in South Africa into a single modelling platform. In addition, the workforce distribution of the country is incorporated into the same platform as a sink for the human resource capital emanating from the education system. The applicability of the framework is explored in terms of aiding policy and decision makers by projecting the long-term effects that changes in throughput rates within the education system are anticipated to have on the subsequent workforce distribution of the country. An instantiation of this framework is implemented on a computer as a concept demonstration. This implementation is applied to a real-world case study which focusses on the impacts of school dropout rates as a result of teenage pregnancies.
  • Thumbnail Image
    Item
    A systems engineering approach : the application of lean thinking to support sustainability transitions in healthcare.
    (Stellenbosch : Stellenbosch University, 2023-02) Cromhout, Bianca; De Kock, Prof Imke; Stellenbosch University. Faculty of Engineering. Dept. of Industrial Engineering.
    ENGLISH ABSTRACT: Sustainable healthcare systems have become increasingly difficult to achieve because of the large amount of competition in the healthcare industry. The healthcare industry needs to move away from the current situation to deliver higher quality, full-access, affordable, and sustainable healthcare services. The status quo of sustainability transitions in healthcare is currently lacking in drivers which support the socio-technical transition to increased sustainable states. Sustainability in healthcare is a relatively novel concept, but it contributes to solving some of the increasing challenges faced in the healthcare industry. By increasing the economic-, social-, and environmental sustainability in healthcare systems, a significant amount of waste can be eliminated while achieving the sustainable development goals set out by the United Nations to be met by 2030. Lean implementations in healthcare systems have proven difficult because the improvements are not maintained, and the system tends to return to its previous unsustainable and non-lean system state. Thus, healthcare systems, as socio-technical systems, are deemed unsustainable. Socio-technical transitions in healthcare systems have increasingly been analysed to understand how they can be designed to increase sustainability and thus assist in achieving sustainable development goals. Given this global sustainability challenge in healthcare systems, it is deemed necessary to develop methods and approaches to ease the transition process to more sustainable system states. Lean thinking and sustainability are interconnected regarding their objectives and aims in system processes. Therefore, incorporating lean thinking into sustainability transitions can strengthen the value creation of system processes by efficiently allocating and consuming resources while ensuring waste elimination during system processes. Thus, this research aims to use lean thinking to support the progression of sustainability transitions in relation to healthcare systems. Literature has proven that lean implementation is a strong driver for increased sustainability. Thus, implementing lean thinking into sustainability transitions strengthens the sustainability transition. This is achieved by developing the lean thinking for sustainability transitions in healthcare (LT4STHC) framework, which uses the author’s developed methodology and LT4ST index to determine which lean thinking approaches or principles could be used to address specific aspects of sustainability transitions in relation to healthcare systems. These aspects include but are not limited to landscape tensions, regime stresses, niche pressures, transition weaknesses, and transition failures. The developed framework, methodology, and index were evaluated in three ways. The framework, methodology, and index were assessed against the requirement specifications for its development. The self-assessment demonstrated that the framework, methodology, and index met the stipulated requirement specifications for its development. Interviews were conducted with subject matter experts (SMEs) in lean, healthcare, or sustainability and sustainability transitions. SMEs verified the theoretical accuracy and tenability of the framework, methodology, and index content. The SMEs were requested to complete questionnaires. A further evaluation of the developed framework, methodology, and index was conducted through a practical application in the form of a case study. Finally, the case study application of the framework, methodology, and index demonstrated its applicability, practicability, and usability. The LT4STHC framework, methodology, and LT4ST index achieved the intended goal of implementing lean thinking approaches and principles into sustainability transitions to support its progression towards an even greater sustainable state. The overall evaluation of the framework, methodology, and index demonstrates that the developed research products achieve the stated research aim and provide assertion to using lean thinking to support sustainability transitions in healthcare.