https://repository.cuk.ac.ke/handle/123456789/617 2026-04-14T19:11:24Z 2026-04-14T19:11:24Z Mung’are Njeri, Kennedy Anyika, Emma Hadullo, Kennedy https://repository.cuk.ac.ke/handle/123456789/1852 2026-01-07T11:19:09Z 2025-01-01T00:00:00Z

Machine learning model for treasury bill yields prediction in Kenya. Mung’are Njeri, Kennedy; Anyika, Emma; Hadullo, Kennedy In this paper, we investigated the issue of forecasting the yields of treasury bills in the Kenyan financial market which is both volatile and complicated, and which traditional models of forecasting may fail because of non-linear behavior. We developed, trained and tested a hybrid machine learning model to improve the predictive power and stability of the model by integrating ARIMA to analyze linear trends, Support Vector Machines (SVM) to capture non-linear interdependencies, and Facebook Prophet (FB Prophet) to capture seasonality and handle missing data. The methodology consisted of obtaining information at the Central Bank of Kenya (CBK) of Treasury bill yields between July 2022 and June 2024. Models were trained and tested on performance measures, namely Mean Absolute Error (MAE), Mean Squared Error (MSE), Root Mean Squared Error (RMSE), Mean Absolute Percentage Error (MAPE), and Mean Absolute Scaled Error (MASE) and cross-validation was used to increase reliability. The findings indicated that Gaussian Copula ensemble model is a more effective model in predicting 364-day Kenyan Treasury bills yields. The hybrid model generated the least Mean Absolute Error (MAE) of 0.1187 compared to best-performing individual model, SVM which had an MAE of 0.1806. The paper concludes that this combination of linear, non-linear, and seasonal-trend models using the specific advantages of each model can offer more reliable and robust forecasts as compared to traditional ones. The model can assist in making intelligent decisions and risk management as well as formulating effective economic policies. A research article published in the Global Journal of Engineering and Technology Advances

2025-01-01T00:00:00Z Kiprotich Sigei, Pius Mbandu Angolo, Shem Omala, Andrew https://repository.cuk.ac.ke/handle/123456789/1851 2026-01-07T08:20:19Z 2025-09-25T00:00:00Z

To Strengthen the Cybersecurity Posture of SACCOs in Kenya by Assessing Current Practices, developing a CTI Sharing Platform, And Formulating Supportive Policy Guidelines Kiprotich Sigei, Pius; Mbandu Angolo, Shem; Omala, Andrew The study investigated to strengthen the cybersecurity posture of SACCOs in Kenya by assessing current practices, developing a CTI sharing platform, and formulating supportive policy guidelines and was based on the following research objective: Creating a platform for sharing Cyber Threat Intelligence (CTI). The research was based on the following research questions: What design and implementation strategies would make a CTI sharing platform viable for SACCOs? The study was based on the Diffusion of Innovations (DoI) Theory developed by Everett M. Rogers in 1962 which explains how, why, and at what rate new ideas and technology spread through cultures, institutions, or organizations and is highly applicable to the design and adoption of a CTI platform because it focuses on how innovation is communicated, the factors influencing adoption, and the roles of various stakeholders issues central to implementing CTI among financial cooperatives like SACCOs.The study targeted 20 Saccos, 120 ICT staffs and 5Management Heads. Census sampling was used to select all the Saccos, the Management Heads and ICT Staff. Anova was used for inferential statistics. Questionnaires and focus group discussions (FGDs). The questionnaires served as structured tools for gathering quantitative data, while the b) from ICT staff while FGDs were used to obtain qualitative insights and more in-depth perspectives on SACCO operations and the challenges they face from Management Heads. This combination allows for a comprehensive understanding of the research subject. Findings indicated Table 3 shows that there was a statistically significant difference between groups as determined by one-way ANOVA (F(4,114) = 18.348,p=.000), (F(4,114) = 15.794, p=.000), (F(4,114) = 12.643, p=.000).Out of the 10 factors used to investigate Creating a platform for sharing Cyber Threat Intelligence. All of them show that there was a strong significance implying that Creating a platform for sharing Cyber Threat Intelligence of Saccos has some influence on improved Cyber security posture. The study recommended: The rollout of the CTI platform should be phased starting with willing SACCOs for pilot testing and refine based on feedback before broader implementation and smaller SACCOs should be supported through partnerships or donor subsidies. Regular cyber briefings, joint simulation exercises, and quarterly feedback sessions should be institutionalized to promote SACCO cooperation. A research article published in the International institute for science technology and education organization.

2025-09-25T00:00:00Z Sawe Chepkogei, Sarah Wanjoya, Anthony Kipkebut, Andrew https://repository.cuk.ac.ke/handle/123456789/1850 2026-01-07T07:25:48Z 2025-01-01T00:00:00Z

Deep Learning Approaches to Multimodal Sustainable Report Analysis Sawe Chepkogei, Sarah; Wanjoya, Anthony; Kipkebut, Andrew This review paper explores the application of deep learning techniques for analyzing multimodal sustainable reports, with a particular focus on enhancing categorization accuracy and deriving deeper ESG insights. Sustainable reporting integrates environmental, social, and governance (ESG) data, often presenting information in diverse formats, including text, tables, images, and charts. Traditional analysis methods, relying heavily on manual coding and keyword-based algorithms, struggle with the complexity, heterogeneity, and dynamic nature of such data, leading to inaccuracies and inefficiencies. Deep learning, with its capacity to learn intricate patterns from high-dimensional and varied data sources, offers promising avenues for automated, comprehensive, and insightful analysis. This paper provides an overview of existing deep learning models (e.g., Transformer Models, Recurrent Neural Networks, Convolutional Neural Networks, Fully Connected Neural Networks) and architectures pertinent to multimodal data integration and analysis, identifies current challenges and limitations in their application to sustainable reports (such as data scarcity and the need for explainability), and proposes future research directions to enhance the efficiency and accuracy of ESG data extraction and interpretation, aiming to establish a standard for automatic sustainability report processing A research article published in the fifth dimension research publication

2025-01-01T00:00:00Z