SU+ Digital Repository

SU+ is an online repository for the preservation and promotion of assorted digital content at Strathmore University

Off-Campus Access to restriced resources (including the ExamsBank) now requires registration using an @strathmore.edu email address

Authentication is NOT required for On-Campus Access to content

Photo by @inspiredimages

Communities in DSpace

Select a community to browse its collections.

Now showing 1 - 5 of 7

Recent Submissions

  • Thumbnail Image
    Item type:Item,
    A Machine learning model for human population forecasting: case for Kenya
    (Strathmore University, 2024) Mete, M. O. O.
    The growth of a country’s population can be a complex issue that has a significant impact on the development and sustainability of countries all over the world. In Kenya, the population is growing rapidly, which is putting a strain on the resources of the country, such as land, water, and infrastructure. The currently used methods of forecasting population growth, such as censuses and mathematical models, are costly, time-consuming, and not consistently accurate. The aim of this study is to develop a ML algorithm to forecast population growth in Kenya more accurately compared to the models currently being used. In this study, seven different machine learning models were examined Artificial Neural Networks, Random Forest, Logistic Regression, Support Vector Machines, Linear Regression, Decision Trees, and K-Nearest Neighbor to determine their effectiveness in predicting the population of Kenya. A variety of factors that impact population growth were considered, such as fertility and mortality rates, life expectancy, net migration, economic growth, access to healthcare and education, and gender equality. All models were built using the Scikit-Learn library and demonstrated impressive accuracy, but the top performers were Artificial Neural Networks, Random Forest, and Linear Regression. Of these, Linear Regression stands out as the best performer overall with a MAPE of 0.0179% and an accuracy of 0.9977% when tested with new data. This is a significant improvement over the other models, which showed slightly lower accuracies.
  • Thumbnail Image
    Item type:Item,
    A Food recommendation system for weaning of children in Kenya using rule-based technique
    (Strathmore University, 2024) Ndemo, D. M.
    Childhood malnourishment is a key worldwide health concern that affects millions of children globally. It can lead to stunting, wasting, and underweight conditions, as well as micronutrient deficiencies. These conditions can have far-reaching consequences, including stunted growth and development, suboptimal academic performance, and compromised overall health. One major cause of childhood malnutrition is poor feeding practices, particularly during the weaning stage. Parents and caregivers often lack the knowledge and resources they need to provide infants and young children with the balanced diets they require. There is also a large human resources gap in the Kenyan healthcare system, where there aren’t enough nutritionists and dietitians to attend to the population and give professional child feeding advice. A way to solve this knowledge gap has been to develop food recommendation systems that help users in making more informed food choices based on their current health status. Many of these systems are tailored for adult populations such as patients with chronic diseases. This study developed a food recommendation system that is tailored to the specific needs of a child, considering factors such as age, weight and height. The system sought to utilize rule-based technique to develop a food recommendation system that would serve as a decision support system for parents and caregivers. The rule-based system was built using Experta, and contained in a full-stack web application that was developed using Flask and React. A comprehensive and diverse food database was adapted from the Kenya Food Composition Tables. The system provided tailored nutrition feedback on amount and frequency of feeding, as well as nutritionally balanced food recommendations in the suggested meal plan. This system not only considered calorie needs but also emphasized nutrient diversity to ensure that children are getting the key micronutrients they need. The system is also usable by healthcare workers to fill the nutrition technical skills gap in healthcare facilities. Keywords: nutrition, weaning, information science, informatics, rule-based technique, decision-support system, recommendation systems.
  • Thumbnail Image
    Item type:Item,
    A Bi-lingual counselling chatbot application for support of gender based violence victims in Kenya
    (Strathmore University, 2024) Mutinda, S. W.
    Gender-based violence (GBV) remains one of the highest prevailing human rights violations globally, surpassing national, social, and economic boundaries. However, due to its nature, it is masked within a culture of silence and causes detrimental effects on the dignity, health, autonomy, and security of its victims. The prevalence of GBV is fueled by cultural nuances and beliefs that justify and promote its acceptability. The stigma surrounding GBV in addition to fear of the consequences of disclosure deter victims from seeking help. Additionally, the resources available for addressing GBV such as legal frameworks and recovery centers are limited. Technological approaches have been established to tackle GBV as intermediate and supplementary support for victims as part of UN-SDG 5. Conversational Agents such as Chomi, ChatPal, and Namubot have been developed for counselling of GBV victims who struggle with disclosing their predicament to humans. The existing chatbots, however, are not a fit for Kenyan victims because they utilize languages such as Swedish, Finnish, Isizulu, Setswana and Isixhosa in addition to incorporating referral services specific to their regions. This research addressed this gap by developing a chatbot application suitable for the Kenyan region for counselling of GBV victims using both Kiswahili and English, the languages predominantly used in the country, in addition to including contacts to referral services within the country. The methodology utilized involved the development of a chatbot application based on Rasa open-source AI framework by training a model using a pre-processed counselling dataset. The performance of the model was evaluated using NLU confidence score to determine the model’s certainty in its intent identification and a confusion matrix was generated which with 80% and 20% training and testing data split resulted in 100% classification threshold accuracy. Python’s Fuzzy Matching Token Set Ratio score was also used to determine the response which best matches the input with results indicating satisfactory performance of the model ranging between 63% and 92% for GBV queries input. The developed model was then integrated into a web application as the user interface for user access and interaction with the model hence achieving the research objective of developing a chatbot application to conduct counselling for GBV victims in Kenya using English and Kiswahili languages. Keywords: Gender-based Violence, stigma, chatbot, Rasa open source, NLU Confidence Score, Fuzzy Matching Token Set Ratio score
  • Thumbnail Image
    Item type:Item,
    Factors influencing the use of modern technology by microfinance banks and Credit-only microfinance institutions
    (Strathmore University, 2024) Kivati, W.
    Financial inclusion aims to ensure that everyone, including the poor, has access to financial services, thereby promoting economic growth and development. Financial institutions have adopted new technologies to accelerate financial inclusion. These technologies include cloud computing, blockchain, artificial intelligence, machine learning, deep learning and robotic process automation. However, given that technology adoption depends on various aspects from the rate of technological changes, institutional features, products and even the nature of clients for microfinance banks and institutions, there is little empirical evidence on the rate of adoption and relevance of new technologies by microfinance banks and credit only institutions. The three main objectives of the study were first, to assess the level of adoption of new technologies in financial inclusion, identify organizational features that influence the type of new technologies adopted and obtain the perspectives of the microfinance banks and credit-only institutions on these new technologies. This study was anchored on Diffusion of Innovation and Financial Intermediation theories, The main population was 13 Microfinance banks licensed by the Central Bank of Kenya as at December 2022 and the 34 Credit only microfinance institutions as listed by the Association of Microfinance Institutions in Kenya in 2022. Primary data was obtained using an online questionnaire and secondary data was obtained from available annual reports for 2022. Both descriptive and multivariate analysis were carried out aided by multinomial logistic regression to establish the organizational factors that may influence the adoption of new technologies. Response was obtained from 39 organizations. Key findings were that all organizations have adopted artificial intelligence, which is ranked as the best technology to promote financial inclusion. However, even though other technologies have been adopted, robotic process automation was the least adopted. Board size reported a significant and positive association with machine learning technology, while profitability, poor asset quality and capital adequacy reported a significant and positive association with deep learning technology. Microfinance banks have adopted cloud computing at a lower rate as compared with credit only microfinance institutions, while MFBs adopt deep learning at a higher rate than that of Credit Only Microfinance institution. Finally, more older organizations have adopted cloud computing as compared to the younger ones. Respondents explained that the main motivation for adopting new technologies was to expand the customer base and reduce operational costs. However, the major challenge of adopting new technologies was costs, due to resource constraints by Microfinance banks and Credit only financial institutions. The key concern for respondents was the fact that customers prioritize using new technology to borrow, with little use of the other services in financial inclusion. These findings are important as they provide empirical evidence on the best technology that aids financial inclusion and areas where key stakeholders can focus to enhance the use of new technologies to promote financial inclusion. Further studies are necessary to include all stakeholders in financial inclusion, with main stakeholder being the customer, to determine the customer experience.
  • Thumbnail Image
    Item type:Item,
    An Evaluation of the prioritization of sustainable finance projects by commercial banks in Kenya
    (Strathmore University, 2024) Riziki, R. W.
    Commercial banks in Kenya are increasingly turning their attention to sustainable financing, influenced by global trends in sustainable finance and increasing focus on environmental, social, and governance (ESG) factors. While this shift indicates a positive direction towards sustainable financing and resource availability to meet the country's sustainable development goals, it remains unclear whether banks have prioritized financing for renewable energy, green infrastructure, social impact projects and other sustainable endeavors. Therefore, this study aimed to achieve the following specific objectives: to determine the prioritization of sustainable finance projects by commercial banks in Kenya; to establish the effect of bank characteristics on prioritization of sustainable finance projects by commercial banks in Kenya and to examine the effect of managers’ perspectives on prioritization of sustainable finance projects by commercial banks in Kenya. The target population comprises 38 business development managers from commercial banks, as they play a direct role in implementing sustainable finance practices within commercial banks in Kenya. The collection of primary data was facilitated through semi-structured questionnaires, whereas secondary data was primarily sourced from the annual supervisory reports and audited financial statements of commercial banks for the year 2022. Descriptive and multi-linear regression statistical analyses used to analyze the collected data. The peer emulation theory of sustainable finance and the system disruption theory of sustainable finance provided anchorage to the study. The study is significant for policy managers in the financial sector, both at the commercial bank and government levels, and for scholars, the study contributes to a deeper insight on priority areas for sustainable project finance and factors influencing managers' perceptions of green financing beyond profitability considerations. The study established that commercial banks prioritized education, health and enterprise projects while bank characteristics and managers’ perception were all found to have significant effect on periodization of sustainable finance projects. It was recommended that commercial banks need to identify the various challenges in adaptation of sustainable finance to ensure that all drawbacks are addressed and that the Commercial Banks establish priority areas and projects for sustainable finance.