KCA University Institutional Repository
Not a member yet
1075 research outputs found
Sort by
N-beats Deep Learning Transformer Model For Nowcasting Consumer Price Index
Get PDFAccurate modelling of time-series data is vital across various domains, particularly in
economic forecasting, such as predicting inflation rates. With inflation data typically released
monthly, the limited number of observations poses a challenge for traditional modelling
techniques. This study explores the applicability of the Neural Basis Expansion Analysis for
Interpretable Time Series Forecasting (N-BEATS) transformer architecture to predict the
Consumer Price Index (CPI). Transformers, commonly pre-trained on extensive datasets,
offer promising capabilities for fine-tuning to specific tasks, even with limited data. In this
research, we aim to replicate the N-BEATS transformer model architecture, utilizing monthly
CPI data from the Kenya National Bureau of Statistics (KNBS). The analysis includes
exploratory data analysis (EDA) to uncover patterns and trends, followed by model
evaluation using Root Mean Squared Error (RMSE) and Mean Squared Error (MSE). This
research endeavours to provide an alternative approach for inflation predictions to
conventional deep learning and the traditional statistical modelling methods
Triangle Cevian and Side Relations for The Concurrent Case and The General Non-Concurrent Case
Get PDFI began this research study by first going through some existing work on triangle geometry and I came across
some interesting theorems, namely Ceva’s theorem, Menelaus’ theorem, Steiner-Routh’s theorem and Van
Aubel’s theorem. By studying the above theorems and through some friends I realized that I could develop a new
approach of studying and analyzing the cevian and side segments of any triangle using a set of six linear equations
that I have derived in this paper.
The main contribution of this study is the proving Ceva's theorem and Menelaus' theorem, using a set of six
equations derived using vectors. The equations are based on the proportions of the sides and cevians of a triangle
and provide a unique and unconventional approach to solving problems in this field. One of the unique aspects
of this approach is the use of vectors to derive the six equations.
This paper presents the equations together with their derivations. I have shown how the six equations can be used
as the basis of proving some famous triangle theorems. In addition to proving these existing theorems, I have also
proven some relatively uncommon results in triangle geometry that can be useful for further research in this area.
This therefore shows that these equations have the potential to reveal even deeper concepts on triangle Geometry
that may have previously been unknown in triangle geometry
Detecting Data Exfiltration Anomalies in Academic Networks Using the Isolation Forest Algorithm
Get PDFAcademic networks face increased risks of data exfiltration due to sensitive personal information and research data. Traditional supervised detection models rely on labeled datasets which are often unavailable in resource constrained institutions. This study investigates the applicability of the unsupervised Isolation Forest algorithm for detecting anomalous network traffic indicative of data exfiltration. The research utilized the CICIDS2017 dataset focusing on the Thursday-Working Hours-Afternoon-Infiltration subset. Key features including Flow Duration, Total Fwd Packets, Flow Bytes/s, Flow IAT Mean, and Destination Port were preprocessed and normalized for modeling. The model achieved a precision of 1.00, recall of 0.99 and F1-score of 1.00 for anomalous traffic detection successfully identifying approximately 4.8% of flows as anomalous. Comparative analysis with previous methods, including supervised Random Forest and SVM demonstrated that Isolation Forest offers competitive accuracy with lower computational overhead and does not require labeled data. The findings highlight the algorithm’s suitability for academic network monitoring, providing an effective early warning mechanism while emphasizing the importance of threshold tuning to reduce false positives
The Influence of Church Sponsorship on Organizational Culture in Private Universities: A Case of Nairobi, Kenya
No full textThis study examines how church sponsorship influences the organizational culture of private universities in
Nairobi, Kenya. It explores the impact of governance involvement and material support on institutional values,
leadership, and autonomy. Guided by Resource Dependence and Stakeholder Theories, a correlational research
design was used. Data were collected from 215 respondents across six church-sponsored universities using
structured questionnaires. Denison et al.'s (2014) Organizational Culture Survey measured organizational culture.
Church sponsorship shapes university culture through governance participation and material contributions.
Sponsors influence governance via board representation, policy formulation, and leadership appointments.
Material support includes financial aid, infrastructure investments, and scholarships. The study evaluates how
these factors contribute to institutional identity and operations. Findings reveal a moderate positive correlation
between church sponsorship and organizational culture. Governance involvement (r = 0.247, p < 0.01) and
material support (r = 0.265, p < 0.01) significantly enhance institutional culture. While governance input
strengthens institutional identity, excessive administrative influence may threaten autonomy. Material support,
particularly financial aid and infrastructure, plays a critical role in shaping university sustainability. These
insights contribute to discussions on faith-based higher education governance. Strategic governance by church
sponsors fosters a strong institutional culture, but direct administrative control should be minimized. Sponsors
should prioritize long-term infrastructural investments aligned with institutional goals. Future research should
explore mediating factors such as leadership styles to deepen understanding of faith-based university governance
Post-Devolution Household Healthcare Expenditures in Rural Kenya
No full textIntroduction: Despite improvements in a country's income during the era of decentralization, catastrophic expenditures persist. This study aimed to establish the determinants of household healthcare expenditures in rural Kenya. Methods: The study utilized data from the Kenya Household Health Expenditure and Utilization Survey (2018). A multiple regression model was employed to estimate the impact of respective determinants on post-devolution health expenditures in rural Kenya. The Ordinary Least Squares (OLS) estimation technique was adopted. Results: The gender of respondents, marital status, medical insurance, and chronic illness were found to be positively related to health expenditures, whereas education levels (primary, secondary, and higher levels) and wealth index (second and third wealth quintiles) were significant predictors but had a negative relationship with health expenditures. Recommendations: The study suggests promoting gender equality in healthcare access and implementing incentives and training programs to encourage men to practice preventive care, thereby reducing hospital visits. Additionally, the study recommends the creation and implementation of awareness programs across organizations, schools, and government agencies. Empowerment programs should be established to help the population lower hospital visits, consequently reducing healthcare expenditures. Furthermore, the government should increase the number of public health facilities to enhance access to subsidized services in rural areas
An ensemble deep learning judgement prediction model for civil Cases in Kenya
Get PDFThis study develops and evaluates an ensemble deep learning model combining Convolutional
Neural Networks (CNN), Bidirectional Long Short-Term Memory (BiLSTM) networks, and an
Attention Mechanism (AM) to predict judgments in Kenyan civil cases. With Kenya's judiciary
facing a backlog exceeding 400,000 cases, this research addresses critical efficiency and
consistency challenges. The CNN+BiLSTM+AM architecture extracts key textual features from
legal documents, captures sequential dependencies in legal arguments, and prioritizes relevant
information through attention weighting, providing both accurate predictions and interpretable
results. Using stratified sampling across court levels, the study analyzes civil cases to identify
influential predictors of judicial outcomes, including legal representation disparities, citation
patterns, and procedural factors. Results demonstrate the model's superior performance compared
to baseline approaches, with implications for case management, resource allocation, and access to
justice. By providing data-driven insights into judicial decision-making, this research contributes
to addressing systemic inefficiencies in Kenya's legal system while establishing a methodological
framework applicable across similar jurisdictions. The findings support Kenya's judicial reform
efforts by offering an innovative, technologically driven approach to enhancing transparency,
consistency, and efficiency in civil litigation
Relationship between Work Environment and Employee Performance among Public Servants Attending Senior Management Course in Kenya
No full textPurpose:The aim of this study was to establish the relationship betweenwork environmentandwork performance of employees in public service in Kenya. This was necessitated by the numerous challenges faced by public servants amidst the budgetary constraints and increased taxes making the work environment laced with high stress levels that are either work-related or personal. The study therefore sort to determine the factors within the work environment and how they influence an employee’s work performance.Methodology:The research design adapted wasuse of cross-sectional research survey, the target population was Public Servants represented by KSG Senior Management Course class 409/2023. The sample was 76 of the 112 public servants in the SMC 409/2023 class selected through simple random sampling. Data was collected using structured questionnaires, data analysis done descriptively and inferentially using Microsoft Excel and SPSS version 27. The results were presented through use of pie charts and tables. Findings:96.1% percent of the respondents believed that the work environment positively affected their jobperformance, which is 72 respondents, while 1.3% believed that it does not, which is only one respondent.Tworespondents wereunsureifthe workenvironment affectstheirjobperformance.Inthemeasurement oftheextent oftheworkenvironmentinfluencingtheirperformance,59.7%ofthem(46) agreed that it has verystrong effects. 24.7% (19) respondents believed that work environment has astrong impact on their performance, 7.8% were not sure if it has or doesn't, 5.2% (4) respondents disagreedthat each has an effect on the performance,while two people strongly disagreed if it has which is 2.6percent. 46.8%, thatis 36 people, were satisfied with their current work environment. 6.5%, which is five people, were very satisfied with their current work environment. 23.4%, 18 respondents, were neither satisfied nor dissatisfied with their current work environment, 16.7% (13) respondents were dissatisfied with their current work environment, and 5, 6.5%, were very dissatisfied with their current work environment.Unique contribution to Theory, Practice and Policy:This study findingswere important for theory because they brought forth new information about the levels of work performance among public servants. For practice, the study will guide on measures that can be done as recommendations to improve work performance and In Policy, the public service can utilizedata from this study to improve on their work place policies to inculcate the unique needs of public servants thus hoping implementation will promote work performance.Keywords
Effect Of Selected Firm Characteristics On Financial Distress Of Large Supermarkets In Nairobi City County, Kenya
Get PDFSupermarkets serve as a vital link between producers and consumers, ensuring the efficient
distribution of a wide range of goods and services across the country. Despite the critical
importance of the supermarket industry, large supermarket chains in Nairobi City County have
been grappling with significant financial stability challenges. The study aimed to determine the
effect of selected firm characteristics on financial distress of large supermarkets in Nairobi City
County. The specific objectives include; to establish the effect of firm size on financial distress
of large supermarkets in Nairobi City County. To determine the effect of leverage on financial
distress of large supermarkets in Nairobi City County. To examine the effect of liquidity on
financial distress of large supermarkets in Nairobi City County. The study was informed by
three theories that include; signaling theory, agency theory and the liquidity preference theory.
The study used explanatory research design. The study focused on seven large supermarkets
that include Naivas, QuickMart, Cleanshelf, Eastmatt, Carrefour, Mathai Supermarket and
Chandarana Foodplus financial records for a period of 7 years (2017-2023) were obtained from
the websites of the seven supermarkets and their annual reports, which are maintained by the
Retail Trade Association of Kenya (RETRAK). The study collected secondary panel data from
2017-2023 for 7 large supermarkets in Nairobi using a data collection checklist. It analyzed the
data using descriptive statistics and panel regression to examine the effects of firm size,
leverage, and liquidity on financial distress. Diagnostic tests like multicollinearity, normality,
heteroscedasticity, stationarity, autocorrelation, and Hausman test were conducted. The
findings were presented using tables and discussed in light of existing literature, highlighting
implications for theory and practice. The study found that firm size had a moderate negative
correlation (r=-0.440, p=0.002) with financial distress. The panel regression analysis also
found that firm size had a significant negative effect (β=-1.3214, p=0.015) on financial distress
of large supermarkets in Nairobi City County. The study also found that leverage had a
moderate positive correlation (r=0.377, p=0.008) with financial distress. The panel regression
results further showed that leverage had a significant positive effect (β=0.6206, p=0.035) on
financial distress of large supermarkets. The study also found that liquidity had a strong
negative correlation (r=-0.512, p=0.000) with financial distress. The panel regression analysis
additionally revealed that liquidity had a significant negative effect (β=-2.7411, p=0.000) on
financial distress of large supermarkets in Nairobi City County. The study concluded that firm
size has a negative and significant effect on financial distress among large supermarkets in
Nairobi City County, implying that larger supermarkets are less likely to experience financial
distress. Leverage was found to have a positive and significant effect on financial distress,
suggesting that highly leveraged supermarkets are more susceptible to financial challenges.
Liquidity was shown to have a negative and significant effect on financial distress, indicating
that supermarkets with strong liquidity positions are better equipped to handle unexpected
financial hurdles. These study shows the crucial role of effective financial management in
promoting the stability and long-term sustainability of the supermarket sector in Nairobi City
County