Repository logo
 

Theses and dissertations (Accounting and Informatics)

Permanent URI for this collectionhttp://ir-dev.dut.ac.za/handle/10321/4

Browse

Filters

2020 - 20212

Settings

Subject: search.filters.subject.Mobile commerce

Search Results

Now showing 1 - 2 of 2
  • Thumbnail Image
    Item
    Image content-based user preference elicitation for personalised mobile recommendation of shopping items
    (2021-10-26) Oyewole, Stanley Ade; Olugbara, Oludayo O.
    Personalised recommendation of product items has been recognised as an exciting snug suggestion for an individual customer. This is required to meet the preferences of an individual customer and improve the sales of merchants. Most current research works in content-based recommendation heavily relied on an orthodox 2-dimensional “user by item” data structure has been used extensively in different application areas for product items recommendation. However, this structure is limited in delivering personalised recommendations to mobile customers because of the inherent “problem of concept drift” that can result in degrading the performance of a recommendation system. This research work introduces an image content-based preference elicitation model based on the approach of supervised machine learning to deliver personalised product items recommendation to mobile customers. This model of product items recommendation leverages the extraction of multiple aspects of item dynamic features to characterise the preferences of mobile customers. This will help mobile customers and nomadic to pervasively discover product items that are most relevant to their interests and reduce barriers to purchase. To start with, a new image-based item classification framework that leverages a novel 4-dimensional colour image representation and Eigen-colour features is built to realise efficient item-class features. The framework is devised to realise a timedependent item relevance score for selecting a set of product items of interest. These features were integrated with other features such as price, location, and incentive associated with a product item to improve the performance of a shopping recommendation system. This is to build the proposed design towards addressing the concept drift problem and large recommendation space problems often associated with the orthodox items recommendation systems. Experimental results of testing an implementation of the proposed item classification framework have shown a recommendation system to produce low-dimensional item features and an implicit shortterm preference profile for a new system user with recommendation accuracy of 92.2% on popular PI100 e-commerce shopping items corpus. Moreover, another experiment on item-based multiple criteria decision-making techniques has revealed that multiple factors can adequately address the concept drift problem. The proposed technique spawns better top-5, top-10, and top-15 rank personalised recommendation accuracy results when compared to the orthodox content-based approach. Finally, as a proof of concept, an imaging interface that anchors the proposed framework in a client-server system was simulated on a mobile phone
  • Thumbnail Image
    Item
    Developing a framework for business analysis of public eservice systems
    (2020-12-02) Naicker, Shivani; Singh, Alveen
    The emergence of the fourth industrial revolution (4IR) digital era is relentlessly morphing habits of social interaction and conducting business. Organizations within the multitude of sectors which constitute a nation’s economic engine are forced to respond to this evolution. Governments the world over are under constant pressure to improve the efficiency and overall effectiveness of the means by which services are delivered to citizens. Public eservice is an interactive internet based service provided by Government to their citizens. Some of these services include viewing and payment of utility bills, application for new services such as, water and electricity, renewal of motor vehicle licences, supplier registrations, submission of tenders, reporting of faults and viewing of buildings plans. As Government gears up to heed the call for growing service delivery demands against the backdrop of 4IR, there has been a marked accelerated effort in the implementation of several information and communication technology (ICT) based constituent service delivery systems. In crafting and optimizing such systems, business analysis is a crucial early stage. Literature portrays largely ineffective business analysis as a major contributing factor to the alarming high failure rate of modern day public eservices systems. Compounding the above is a lack of widely accepted practice guidelines and a scarcity of robust academic literature supporting business analysis in the public eservices domain. This dissertation is driven by the primary aim of the development of a business analysis framework specifically for public eservice projects. Following a critical analysis of literature, a set of components are distilled to form a theoretical framework of practice guidelines. The components derive from knowledge areas deemed critical for business analysis and present essential tasks, tools and techniques for Business Analysts plying their expertise in public eservices projects. The Design Science methodological approach further hones the framework after an iterative process of feedback and adjustment. A handful of Business Analysts are purposively selected for focus group participation and serve as change agents in the Design Science cycle. The Design Science cycle evolved the business analysis framework to an eventual seven components namely, Project Committee, Business Analysis Plan, Requirements Analysis, Business Collaboration, Requirements Changes, Solution and BA Review. The ADVIAN classification method provides an analytical tool for identifying the relationships between these components and the components that are vital for the effectiveness of the framework. The impact of change to one component on the other components is highlighted and this analysis confirms the robustness of the inclusion of components in the eventual framework. Further, the results of the ADVIAN analysis provides foresight into the impact of changes made to the framework when tailoring to a specific project. This will be of value to project teams wanting to utilize the framework across eservice projects. The use of ADVIAN shows the impacts of changes to the components of the framework when components are altered. It shows the impact of each component on the other. By understanding the current challenges faced by public eservices, it is hoped that the developed framework will offer a contribution to the gap in the business analysis domain with particular focus on the public eservice systems.