MSc in Information Management
Permanent URI for this collectionhttps://rda.sliit.lk/handle/123456789/4071
Students enrolled in the MSc in Information Management programme are required to complete a thesis as part of fulfilling their academic requirements. This collection includes merit-based theses submitted by postgraduate candidates specialising in Information Management. Abstracts are available for public viewing, while the full texts can be accessed on-site within the library.
Theses and Dissertations of the Sri Lanka Institute of Information Technology (SLIIT) are licensed under a
Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License
.
Browse
27 results
Search Results
Publication Open Access AI-Powered Fashion Trend Prediction: A Conceptual Framework and Comparative Analysis Using Social Media and Historical Data(Sri Lanka Institute of Information Technology, 2025-12) De Noyel, K.T.S.P.Fashion trend prediction is a complex process influenced by various factors have a role to play in. With emphasis on data observation and collection within an industry, interest in predicting trends using artificial intelligence (AI) has intensified over time. This paper outlines a theoretical framework of an AI-driven fashion trend prediction system that combines past sales data and social media posts. The model aims to use natural language processing (NLP) to explore Instagram, Facebook, fashion forums, and other fashion-related social media platforms to process information to capture the realtime opinion of the masses and identify trends. [1] At the same time, historical sales performance data, including products sold during seasons, subsequent years, purchasing behavior over time, and other consumer and market trends, assist in predicting demand in the marketplace. [2] The suggested framework describes how AI algorithms, especially machine learning and deep learning models can be used to these two complementary data sources to create actionable insights. When these datasets are combined, fashion trends are forecasted with more accuracy. This will assist brands and retailers in making proactive decisions regarding product and marketing strategies alongside inventory control. In particular, the paper underscores the conceptual architecture of the AI system, explaining the fundamental aspects of forecasting trends, consolidating data, and computation through an algorithm. This forms the basis of other studies that seek to apply AI Systems in forecasting the fashion industry trends while at the same time waiting to see the deployment of such systems. In addition, the challenges alongside ethical implications as well as opportunities for further development within this context strive to reduce the existing gap between fashion business practices and data science are provided.Publication Open Access The Role of Machine Learning Algorithms in Shaping Teenage Social Identity through Curated Digital Experiences.(Sri Lanka Institute of Information Technology, 2025-12) Sajipratha, R.Social media has taken its place as one of the most powerful instruments of the modern digital environment that affects the perception of young individuals towards each other and themselves. Identity formation is a significant developmental condition among teenagers, and due to the individualized algorithms that shape what they view, like, and interact with online, it is becoming more affected by the latter. The paper examines the influence of Machine Learning-based recommendation systems on the social identity of teenagers in the framework of algorithmic curation, and the connection between algorithmic exposure, diversity of content, and identity pressure. The study enables a more profound insight into how Artificial Intelligence impacts social comparison, body image, and self-perception of adolescents by studying the psychological implications of the use of algorithms in personalization. The research design was a quantitative one to analyze the data gathered based on 150 students between age 18 to 19 of an international school in Kandy, Sri Lanka. The research employed an indexed questionnaire, which measured the following: Algorithmic Exposure Index (AEI), Stereotypical Content Reinforcement (SCR), Number of Topics (NTOP), and Body/Identity Pressure (BIP). The data were analyzed using descriptive, correlation and multinomial logistic regression techniques to identify the interaction of these variables and predictive of the emotional and identity related outcomes. Findings showed that more than 60 percent of the subjects especially females indicated that they experienced a lot of social comparison and body pressure following the exposure to the algorithms. Tik Tok and Instagram users reported much more odds of being subjected to appearance and behavioral pressure than YouTube users, thereby affirming that appearance-focused and engagement-oriented platforms enhance conformity and self-assessment. Moreover, negative self-perception at the time of exposure to stereotypical material (high SCR) was strongly related to exposure, and increased diversity of the topic (high NTOP) was a protective factor, decreasing the identity stress and resulting in a more balanced sense of self. The results promote both Social Identity Theory and Algorithmic Bias Theory, showing the Machine Learning systems not only suggest content, but also act as the contributors to the formation of the identity of users by supporting specific social norms and values. Young people who are in algorithmic echo chambers are less exposed to different or anti-stereotypical stories, which results in more limited ideas of attractiveness, popularity, and success. This paper thus lays emphasis on the importance of algorithmic responsibility, ethical design and media literacy interventions. The research will offer a solution to these issues by proposing the Responsible Curation Framework, which is a complex intervention encompassing algorithmic diversity prompts, user-controlled content filters and digital literacy education. Collectively, these measures will help to regain the balance of exposure, self-awareness and encourage psychological well-being in young users. On the whole, this analysis can be discussed as part of the expanding discourse of ethical AI and digital well-being and can serve as a way of starting to change how algorithmic recommendation systems are managed so as to become instruments of conformity instead of instruments of diversity, empowerment, and positive identity formation.Publication Embargo Determinants of Technology Adoption and Its Effect on Service Efficiency and Customer Retention in the Beauty and Aesthetic Services Sector(Sri Lanka Institute of Information Technology, 2025-12) Dharmarathna S.H.H.KDigital transformation has significantly reshaped the service sector, with digital appointment scheduling systems emerging as critical tools for improving efficiency and customer engagement. In the beauty and aesthetic service sector, where service quality, operational smoothness, and client satisfaction are vital, the adoption of such technologies offers the potential to reduce waiting times, minimize scheduling conflicts, and enhance overall customer experience. However, adoption rates vary across organizations due to differences in organizational readiness, user perceptions, and contextual challenges. This study aims to develop and validate a model of the determinants of digital appointment system adoption within the Sri Lankan beauty and aesthetic service sector. Grounded in the Technology Acceptance Model (TAM) and technology adoption literature, the research identifies five independent variables—Service Efficiency, Customer Satisfaction, Organizational & Technical Readiness, Perceived Usefulness, and Perceived Ease of Use—as influencing adoption. The dependent variable is Adoption of Digital Appointment Systems (DASA), while moderating factors such as firm size and role (owner vs employee) are also considered. A quantitative research design was employed, using a structured survey distributed among employees and owners of beauty and aesthetic service centers. Data were analyzed using Partial Least Squares Structural Equation Modeling (PLS-SEM) via SmartPLS. The study evaluates measurement reliability and validity, followed by hypothesis testing of the structural model. Findings are expected to contribute both theoretically and practically by clarifying the key determinants of technology adoption in service industries, while also offering recommendations to managers, practitioners, and policymakers on fostering digital adoption in beauty and aesthetic services.Publication Open Access Assessing the Viability of a Vendor-Driven Framework for Food Waste Management in Sri Lanka(Sri Lanka Institute of Information Technology, 2025-11) Thivithma, A.VFood waste is a pressing global and local issue, with substantial economic, environmental, and social costs. In Sri Lanka, more than 42% of food waste in urban areas originates from restaurants, markets, and slaughterhouses, while expired supermarket products contribute further to the problem. These losses translate not only into financial burdens but also reputational risks for businesses. Globally, the cost of food waste is estimated at USD 1 trillion annually; a reduction of even 25% could feed 870 million people. Against this backdrop, innovative solutions such as digital platforms have gained prominence. Inspired by the internationally successful "Too Good To Go" app, this study explores the feasibility of introducing a vendor-focused digital solution for food waste reduction in Sri Lanka. Using a sample of 220 food vendors (restaurants, hotels, bakeries, supermarkets, and grocery shops), the study investigates vendor perspectives across critical independent variables: economic incentives, technological accessibility, trust and food safety, public image, government support, customer demand, logistics, religious and dietary preferences, and transaction methods. A conceptual framework with six dependent dimensions—Vendor Adoption, Quick Match, Vendor Profitability, Waste Saved, Fair Access, and Stay Strong, was developed. Findings reveal strong vendor interest, with economic incentives, public image, logistics, and government support emerging as dominant drivers of adoption. Context-specific factors such as tri-lingual support, religious labeling, and COD payment options were identified as essential for inclusivity. The study proposes a vendor-driven framework tailored to Sri Lanka, aligning with national waste policies and the Clean Sri Lanka Initiative. This thesis contributes to both theory and practice by providing a structured, evidence-based model for digital food waste management in developing contexts.Publication Open Access Analyzing the Impact of Key Factors on the Likelihood of Cash-on-Delivery Parcel Returns: A Seller’s Perspective in Sri Lankan E-Commerce(Sri Lanka Institute of Information Technology, 2025-09) Panditharathna, S.M. VCash-on-Delivery (COD) remains the dominant payment method in Sri Lankan e-commerce, but it generates disproportionately high return rates compared to prepaid orders. Returned COD parcels impose dual costs on sellers, who must absorb forward delivery fees even when the order is refused, while also incurring inventory, administrative, and reconciliation burdens. Despite the prevalence of COD, there is little structured research that distinguishes between seller-, courier-, and buyer-related drivers of returns in this context. The purpose of this study is to develop and validate a predictive framework that estimates the likelihood of COD parcel returns from the seller’s perspective, and to identify operational levers that can reduce such returns. Three independent constructs are examined: Seller’s Operational Quality, Courier Service Delivery Performance, and Buyer Acceptance Behavior at Delivery. Each construct is operationalized using seller-perspective indicators over a fixed 90-day recall window and measured on a five-point Likert scale. Data were collected through a structured survey of active Sri Lankan e-commerce sellers using purposive sampling, with analysis conducted via Partial Least Squares Structural Equation Modelling (PLS-SEM). The results demonstrate that all three constructs significantly influence the likelihood of COD returns, with courier performance and buyer acceptance behaviors exerting the strongest predictive effects. Findings highlight the critical importance of first-attempt delivery success, pre-shipment accuracy, and effective communication in minimizing return rates. This research contributes a context-specific framework for understanding COD returns in Sri Lanka, offering actionable insights for sellers, courier firms, and policymakers seeking to enhance e-commerce sustainability.Publication Embargo AI-Powered Language Learning Systems: A Study on Personalized Learning for Foreign Language Learners(2025-12) Jayasekara, E.J.K.P.S.P.Artificial Intelligence (AI) is increasingly transforming the field of education, with personalized learning emerging as one of its most impactful applications. This study investigates the role of AI-powered personalized learning systems in supporting beginner-level foreign language learners. The research was motivated by the challenges beginners face in traditional learning environments, such as limited practice opportunities, delayed feedback, and lack of adaptive content. A quantitative survey was conducted with 173 participants engaged in learning German, French, or Japanese using AI-based platforms. The study examined learner demographics, perceptions, effectiveness of personalization, and associated challenges. The conceptual framework positioned AI-powered personalization as the independent variable, learner engagement and competency as mediators, and learning outcomes—measured in terms of retention, motivation, and performance—as dependent variables. The findings reveal that AI personalization has a significant positive effect on both learner engagement and competency, which in turn are strongly associated with improved learning outcomes. Mediation analysis confirms that engagement and competency jointly strengthen the link between personalization and outcomes. While most learners perceived AI tools as engaging and motivating, concerns were raised about technical reliability, privacy, and over-adaptation of content. The study concludes that AI-powered personalization enhances early-stage language acquisition but requires careful refinement to address ethical and technical limitations. Recommendations are provided for educators, developers, and institutions to integrate AI as a supplementary tool while maintaining safeguards around learner data and pedagogical balance.Publication Open Access The Impact Of Organizational Diversity And InclusionInitiatives(D &I) On The Employee Job Satisfaction Of Software EngineersInThe Sri Lankan ICT Sector(SLIIT, 2024-12) Weerasinghe, K.P.H.This study examines the impact of gender diversity and organizational factors on jobsatisfactionamong software engineers in Sri Lanka’s ICT sector. Through a quantitative approach, datawascollected from 500 employees across five prominent companies: PayMedia, Virtusa Corporation,Epic Lanka Technologies, IFS, and Calcey Technologies. The research centers onfivekeyindependent variables: gender diversity, workplace culture, work environment, career developmentopportunities, and policies and procedures. Statistical analyses, including reliability analysisandmultiple regression, were conducted to assess the relationship between these variables andjobsatisfaction levels among employees. Results indicate that gender diversity, workplace culture, work environment, career developmentopportunities, and organizational policies and procedures all exhibit strong positive correlationswith job satisfaction. Specifically, organizations that prioritize gender diversity, cultivatepositiveand inclusive workplace cultures, provide supportive and conducive work environments, establishclear career development paths, and implement well-defined policies significantlyenhanceemployee job satisfaction. The findings highlight that while career development opportunities and organizational policieshave a major impact, gender diversity, workplace culture, and work environment alsoplaycrucialroles in shaping job satisfaction. This study emphasizes the need for a holistic approachinorganizational planning to foster inclusive, supportive, and well-structured environmentsthatenhance job satisfaction and drive performance in ICT companies. Further researchisrecommended to explore additional factors and validate these findings across different sectors.Publication Open Access Investigating the Impact of Smart Whiteboard Usage on Teacher Satisfaction in Secondary Education in International Schools: A Study in Colombo District(SLIIT, 2024-12) Weerasekera, N. S.The integration of educational technology has revolutionized teaching and learning in classrooms worldwide, with smart whiteboards becoming a popular tool for enhancing interactive instruction. While numerous studies have highlighted the pedagogical benefits of smart whiteboard usage, there remains a significant gap in the literature regarding its impact on teacher satisfaction, particularly in specific geographical contexts. This research aims to explore teacher satisfaction with smart whiteboards within the Colombo District, focusing on their use in secondary education. The 21st century has seen the rapid advancement of information technology, which has significantly enhanced the teaching profession. Tools such as smart whiteboards, computers, and online resources have allowed teachers to create more engaging and interactive lessons. Despite the widespread adoption of these tools, particularly smart whiteboards, their effect on teacher satisfaction remains underexplored. This study employs a simple random sampling method to select 350 teachers from five international schools in Colombo. A structured survey will include multiple-choice questions and offer insights into the role of smart whiteboards in improving teaching practices and student engagement. This research seeks to fill the gap in understanding the relationship between smart whiteboard use and teacher satisfaction, providing valuable insights that may inform future technology integration policies and strategies in education.Publication Open Access Development of a Non-Invasive Algorithm for Anemia Detection in Women in Sri Lanka(SLIIT, 2024-12) Senanayake, W.I.UAnemia continues to be a considerable health issue for women in Sri Lanka, impacting physical and cognitive growth, general health, and economic efficiency. Diagnostic methods, like blood tests, are invasive, time-consuming, and could be out of reach for populations with limited resources. A non-invasive algorithm is created to detect anemia in Sri Lankan women in this thesis. The algorithm utilizes readily available clinical and demographic information to decrease reliance on conventional blood tests. According to that ―Development of a Non-Invasive Algorithm for Anemia Detection in Women in Sri Lanka‖ entitled as the research title of this thesis. The research involves data collection from women across varied demographics and regions, combined with vital health parameters and physical indicators relevant to anemia detection. Advanced machine learning models are trained on this data to identify patterns associated with anemia, offering accurate predictions without the need for invasive procedures. A core aim of the study is to enhance early detection, enabling timely intervention and reducing the overall prevalence of anemia among women. The high sensitivity rate of the algorithm allows for effective anemia detection with minimal input data, according to key findings. Furthermore, its non-invasive characteristics make it appropriate for application in rural regions where healthcare resources are scarce. The system successfully provides a non-invasive, accurate, and accessible method for anemia detection, using fingertip imaging and machine learning to predict anemia in real-time. With a compact device integrated into a web app, users can monitor their health easily, while healthcare providers can remotely access patient data for timely interventions. The system’s cost-effectiveness and ease of use make it particularly valuable for resource-limited settings, offering a scalable solution for anemia management and broader public health impact.Publication Open Access Evaluation of Infrastructure as Code (IaC) Approaches for Automated Provisioning and Configuring of IoT Devices in Smart Factory Environments(SLIIT, 2024-12) Weerasekara, W. K. N.The Internet of Things (IoT) area is gaining with time and predictions are showing that Industrial IoT (IIoT) will gain more and more in the future. Here this research was done to find out the best Infrastructure as Code (IaC) tool from model-driven, Terraform and code-centric Ansible for automatic configuring and provisioning IoT devices in large-scale IIoT systems such as automated factory environments. This research has shown the use of IaC within IIoT to automatically provision and configure components of the IIoT system alongside improving productivity, less human involvement in provisioning and configuring components, minimising the errors in device provisioning, costeffectiveness with increased portability and maintainability of the large scale IIoT system with the benefit of the IaC. Furthermore, the research assessed Terraform and Ansible by analysing the elapsed time, resource utilisation, scalability, and error rate, in provisioning and configuring as well as reconfiguring using a prototyped simulated environment for a factory. Also, the research is contributing to the design and development of a cross-platform IaC script generation and execution application including the monitoring capabilities. This tool is named “KFactory Device Provisioner and Configurator”. This application allows to generation of IaC provisioning scripts and executes those with monitoring capabilities as users’ need via a Graphical User Interface (GUI). The tool also has a system monitoring tool that is very helpful to view the variation of CPU usage, Memory usage and inbound-outbound Network usages in a GUI. Furthermore, the tool also collects the provision data to create a Machine Learning (ML) model to predict and show the expected provisioning time, reconfiguring time, CPU, Memory and Network inbound and outbound usages according to the scale of the provisioning tasks based on the host system’s capabilities. Moreover, with the conclusion of this research, the researchers are encouraged to come up with a fine-tuned, production-grade IaC solution for automatic provisioning and configuring IoT devices in large-scale IIoT systems with reduced deployment time, optimized resource utilizations, having scalability, having low error rate, and reduced reconfiguring time.
- «
- 1 (current)
- 2
- 3
- »