KCA University Institutional Repository
Not a member yet
1075 research outputs found
Sort by
The Effect of Mobile Banking Accounts and Deposits on Operational Efficiency of Commercial Banks in Kenya
Get PDFThis study's main objective was to examine the mobile banking's effect on commercial banks'
operational efficiency. The study looked at mobile banking accounts and mobile banking
deposits concerning commercial banks' operational efficiency in Kenya. The research was led
by the unified theory of acceptance and use of technology model (UTAUT) and Technology
acceptance model (TAM). A descriptive research design was used, targeting all the 41
commercial banks. The research adopted a census survey while utilizing secondary data from
Central Bank of Kenya and the commercial banks' annual financial reports in Kenya. Data on
the number of bank deposits mobilized as savings and the number of registered bank accounts.
The study period is from 2010-2018. STATA software was used in data analysis, descriptive and
statistical inferential. The independent variables were measured against the dependent variable
to examine if they affected commercial banks' operational efficiency. Multiple regression
equations estimated the relationship between the variables. Hausman Test was used to specify
the adoption of Random effect or Fixed effect models in panel data. The Hausman tested and
fixed effect model was selected. The diagnostic tests covering heteroscedasticity,
autocorrelation, multicollinearity, and normality tests were also conducted. The findings were
presented using graphs and tables. The results were as follows: mobile bank accounts
(β=0.0365, p>0.05), and mobile deposits (β=0.015, p>0.05). The study concluded that
mobile accounts and mobile deposit had no significant effect on commercial banks' operational
efficiency in Kenya. The study recommended that commercial banks invest more in mobile
deposits since it had a positive relationship with commercial banks' operational efficiency in
Kenya. The study results would enhance the adoption of more efficient financial innovation
products and services in the banking industry that would enhance the overall commercial banks
operational efficiency
Factors Affecting Customer Retention In Courier Companies In Kenya
Get PDFThe main purpose of this research study was to determine factors affecting customer
retention in courier companies in Kenya. “The study was guided by a number of research
questions. Does relationship representative affect customer retention, does credit affect customer
retention, does branding affect customer retention and does cost of switching affect customer
retention in courier companies in Kenya. The study was quantitative and adopt a descriptive
cross sectional survey design which is mainly used in preliminary and exploratory research
studies. Primary data shall be collected from the courier companies using questionnaires. A
population of 253 registered courier companies in Kenya was contacted. Data was coded in
statistical package for social sciences (SPSS) and analysed by descriptive statistics and
inferential statistics. Diagnostics test conducted were normality heteroscedasticity and
multicollinearity and they met the criterion for regression analysis. The findings indicated that
Relationship Representative and Customer retention in courier companies is positively and
significantly related (β=0.315, p=0.000). The findings further indicated that Payment Credit and
Customer retention in courier companies is positively and significantly related (β=0.143,
p=0.048). Product Branding and Customer retention in courier companies is positively and
significantly related (β=0.503, p=0.000). Lastly, the findings indicated showed that Switching
Cost and Customer retention in courier companies is positively but insignificantly related
(β=0.022, p=0.787). The study concluded that relationship representative, payment credit,
product branding had a positive and significant effect on Customer retention in courier
companies. However, the relationship between cost of switching and customer retention in
courier companies was not significant. The study recommends that the courier firms should have
relationship representatives to build customer relationships as they are important because they
increase sales, reduce customer attrition, deliver invaluable marketing, boost employee morale
and turn customers form more market information. The study recommends that the courier firms
can offer reasonable credit to the customers based on their creditworthiness. The study
recommends that due to the high competition, they should continually embark on product
branding. Branding will make a memorable impression on consumers and allow the customers
and clients to know what to expect from the courier firm.
An Application Of Ensemble Learning
No full textThe need to determine house prices beforehand is an important element in making a decision on whether to purchase a house or not. The commonly used price forecasting models are single predictor models but are prone to over-fitting and low accuracy levels emanating from their inability to handle noisy data. We propose a regression based ensemble learning model that incorporates multiple predicting models while using Root Mean Squared Error (RMSE) and R-Squared error to measure model performance. This entails leveraging on extreme gradient boosting (XGBoost), Random forest and Light gradient boosting (lightGBM) algorithms to form base models. Stacking of the models was also used before generating the final model using weighted voting. The dataset used is the Ames housing dataset readily available on Kaggle platform. The results of the study reinforce further that ensemble learning method greatly helps improve accuracy of the model as compared to single prediction model
A Predictive Model Of Climate Sensors Effectiveness On Sustainability Of Subsistence Agriculture: The Case Of Laikipia County
No full textIn contrast to many areas of the globe where farmer posses adequate physical, economic and
social resources to adapt to and moderate effects of climate variation and climate change,
subsistence agriculture in the arid and semi-arid lands (ASALs) of Kenya are particularly
affected in an unfavorable manner by the effects of climate change. This is more so because
of the increasing dependency of a good number of the population on rain fed agriculture as a
source of livelihood and economic income. An effective adaption mechanism to climate
change for sustainability of subsistence agriculture in these areas using communication
technologies is therefore highly important for food security and protection of livelihoods
within the rural areas. The main aim of this study was to model and predict the effectiveness
of climate sensors on the sustainability of subsistence agriculture in Laikipia County, one of
the ASALs in Kenya. The study hypothesized that the current community based strategies
applied by the local farmers are relevant and important to the present-day quest for climate
change adaptation strategies, and that feedback from the stakeholders can generate insight
used to generate an improved predictive model to further enhance this adaptation. The study
therefore conducted a survey study of rural stakeholders in Laikipia farmlands and assessed
the output through descriptive measures. Further, a logistic regression model of variables
constructed from the survey study was used to predict the effectiveness of data
communication technologies such as climate sensors that are currently employed on the
sustainability of subsistence agriculture in these rural areas, using variables such as
geographic extent, temporal scope, precision level, frequency of usage, and cost of
acquisition. The model was be tested through standard measures of goodness of fit such as
Chi-square and adjusted goodness-of-fit index. It is expected that results of this study will be
useful in policy formulations regarding adaptation mechanisms to climate change for
sustainability of rural-based subsistence agriculture
Uplifting Model For Predicting Subscriber Churn Conversion Using Ensemble Learning: A Case Study Of Mobile Telecommunication Sector In Kenya
No full textChurn is the number one topic for Telco’s in Kenya and around the world. Customer churn in the telecommunication industry is still a big problem because emerging new technologies, lower costs, among other factors Churn brings with it many negative repercussions. While churn is a helpful key performance indicator for identifying areas of improvement whether in process or product, it can lead to financial disability eventually as customer acquisition cost are normally more astronomical than trying to please a disenchanted Subscriber. By analyzing churn drivers, we can safeguard the most import asset for a telecommunication company from churning. Predicting subscribers who are most likely to churn is fundamental for telecommunication companies. As a result, churn prediction is an important barometer for business success as well vastly studied and common activities that can be accomplished by machine learning applications for telecommunication industry. Telecommunication companies have since come to a realization that churn prediction only provide predictions but do not provide information for optimal decision making within a business setting. This is where uplift modelling has come to the fore. Uplift modeling is a branch of machine learning which aims at predicting the causal effect of an action such as a retention campaign or a marketing campaign on a given population by considering outcomes from the campaign treatment on that group, involving the sample populations that has been subjected to that campaign or treatment, and a control sample population. The model generated is then utilized to select the segment of population that the campaign would be profitable. This dissertation analyzes the use of ensemble methods in uplift modeling. The researcher will attempt to demonstrate higher performance compared to traditional classification and uplifting techniques. The researcher will attempt to show improved performance are a result of using ensemble classification techniques inculcating the differences in class probabilities in the treatment and control groups. The result being a Novel propensity outcome modification model. Safaricom plc was used as a case study to develop an uplifting for predicting subscriber churn conversion on various pre-existing subscriber segments. The objective of the study was to find the most profitable segment to target after using an ensemble classifier to predict probable churn customers on prepaid subscribers. Anonymized and pseudomized subscriber data was used for the study. The final results show the accuracy and precision of the ensemble predictive classifier and also the uplift scores for the various existing subscriber segments using the novel propensity outcome modification approach that identifies the probable segment to target with a retention campaign
A Model For Assessing The Performance Of Post Graduate Research Supervisors In Kenyan Universities
No full textHigher education has become important in Kenya due to the increase in the number of students, introduction of new courses at the universities and an increase in the number of universities. Our study undertook to create a model that investigated and identified the attributes that can be used to determine the performance of supervisors when assessing post graduate research students’ in Kenyan universities. The study was driven by the desire to evaluate why many post graduate students do not complete their research in a timely manner. The findings of this study can be used as a measure to determine promotions, to improve supervision performance in Kenyan universities, to improve service delivery in the industries and to ensure average or high completion rates of students at the post graduate level in Kenyan universities. The research targeted a population of 20 and more post graduate students and coordinators from Kenyan Universities. Online questionnaires were used to get data from the respondents and Likert scale was used to convert data into numeric values. We investigated whether the supervisor performance can be determined by the supervisor characteristics, student characteristics and use of learning resources and facilities. The data collected from the students and coordinators was analyzed using a system designed using Django web frameworks and data analytics was applicable
A Model For Predicting Students Academic Performance In Public Secondary Schools In Kitui West Constituency
Get PDFIn the present era of data deluge, institutions have accumulated huge amounts of data in their
databases. Educational institutions all over the world are not an exception, having as well
accumulated large amounts of data in their various educational management information
systems databases of various forms and formats. The accumulation of such data in various
educational institutions has led to the rise of two research fields namely; Educational data
mining and learning analytics in an effort to discover hidden knowledge (insights) that can
greatly improve operations in educational institutions. Among the hidden knowledge include
but not limited to; predicting students’ performance, students’ drop out, discovering students
interest which could avert popular student’s unrest in various institutions etc. This study
seeks to take advantage of such an opportunity and develop a model using dataset obtained
from public secondary schools in Kitui west constituency that can be used to predict students’
academic performance. There has been attempts from various researchers all over the globe
to address this problem. Although such studies achieved some level of success, various
limitation discussed in details in the empirical review militated against the performance of the
earlier models. Desk research methodology was used to extract relevant secondary data from
various schools’ departments within Kitui west constituency. Then preprocessing which
includes feature selection after which the cleaned dataset was loaded to staging Data Lake in
Hadoop. Data was queried from the Data Lake to python using Pyspark where data analysis
procedures took place. Dataset consisting of optimal subset of features was used to train four
machine-learning algorithms: Gradient boost classifier, Random forest classifier, Decision
tree classifier and Deep Neural Network classifier. Generally, Decision tree and Random
forest classifiers registered the best performance overall, with an accuracy of 97%, but after
stratified Kfold cross validation, Decision tree classifier’s performance proved more stable
with an average of 97% compared to Random forest classifier with 93%. Thus, Decision tree
classifier was recommended for deployment in predicting students ‘academic performance
for its reliable accuracy and relatively good precision on predicting the study’s target group.
The developed Model will place students in to two groups: PASS and FAIL. The aim being
to arouse an initiation of intervention from various stakeholders to reduce dismal
performance among public secondary schools in Kitui west constituency
Role of Human Resource Management Practices on Employees’ Retention in the National Museum of Kenya and Kenya National Archives Headquarters
No full textThe Research purposed to establish the role of HRM practices on employees’ retention in the NMK and KNA, Headquarters. The study adopted descriptive research design to conduct investigation, with a sample of 257 participants being arrived at and will be selected using stratified sampling. The first objective of the study sought to establish the role of recruitment process on employees’ retention, showing that when recruitment practice is considered individually, there is high impact of 0.516 on employee’s retention and when used with other practices, the impact is at 29.1% (0.291). The second objective determined the role of performance management practices on employees’ retention, showing performance management to influences employee’s retention by 0.556, and when considered together with other HRM practices improve retention by 15.4% (0.154). The third objective sought to find out the role of reward practices employees’ retention, showing reward practices to improve employees’ retention by 0.668 and when implemented together with other practices contributes up to 49.3% of employees’ retention. Finally, the study established the role of training and development practices on employees’ retention, showing up to 0.582 relationship with employee’s retention and together with other practices, implementation of specific training and development practices contributes up to 35.3% of employees’ retention. The study addressed the objectives of the study, showing that HRM practices like recruitment, performance management, training and development and reward to play a critical role in improving employees’ retention. Therefore, the regression model that can improve the employee’s retention in the ministry of culture, mainly KNA and NMK where data was collected is: Employees Retention= 0.922 + 0.291 Recruitment Practices + 0.154 Performance Management Practices + 0.353 Training and Development Practices + 0.493 Reward Practices + ε. The study recommended that great emphasis be given to reward practices, followed by training and development practices, recruitment practices and performance management practices based on their order of influence on employees’ retention
Relationship Between Mode of Financing and Financial Performance of Deposit Taking Savings and Credit Cooperative Societies in the Lake Region Counties of Kenya
No full textAbstract
Mode of financing is an important factor for consideration when it comes to firm financial performance. Several
studies show that highly leveraged organizations usually do well in terms of financial growth by increasing the
value of a firm, contrary to the MM theorem that argues that capital structure is irrelevant factor to consider since
it does not affect the value of an organization. This study focused on establishing the relationship between share
capital, retained earnings, members’ deposits, debt financing and financial performance of SACCOs in the Lake
Region Counties of Kenya. The study was prompted by the increase in the number of SACCOs in the Lake Region
Counties facing financial difficulties resulting to low returns to investors and in some instances, SACCOs being
de-registered by SASRA for not meeting the SASRA regulations, thus threatening the well being of the lake
region’s economy. The study adopted explanatory research design and the target population was all the 34-deposit
taking SACCOs in the Lake Region Counties of Kenya. Secondary data was obtained from the annual reports and
financial statements of the 34 DT-SACCOs were used for analysis. The annual reports and financial statements
were sourced from the official website of SASRA and the respective official websites of the DT-SACCOs. The
period of study was stretch from year 2015 to year 2019. The collected data was converted into panels and fed into
STATA version 14 for analysis. The data was analyzed using descriptive statistics, correlation analysis and panel
data regression analysis. The study revealed that share capital has an insignificant positive relationship with
performance of SACCOs in the lake region while retained earnings has a significant effect on financial
performance of SACCOs in the lake region. The study also showed that debt financing has a significant negative
effect on financial performance of SACCOs in the lake region. The study recommends DT SACCO management
to exploit internal source of financing such as retained earnings and share capital. It also recommends that DT
SACCOs should avoid expensive debts but instead sought loans with favorable terms
An Adoption Model For Electronic Health Records System In Health Care Facilities: Case Of Siaya County, Kenya
No full textThe electronic health record system offers a number of benefits which can be used to improve service delivery in the health care facilities that have implemented the systems. However, there has been a slow and stagnant adoption of EHR systems in health facilities across Kenya. The main objective of the study was to determine factors affecting adoption of Electronic Health Records systems in health facilities across Kenya and develop a model that could be used to inform implementation of the systems across the country. Siaya County was used as a case study. Collection of Data was done by administering a semi-structured questionnaire to the participants. Accuracy of data was ensured through checking the completed questionnaires before analysis. Analysis was done through the use of SPSS statistical tool. Correlation analysis through cross tabs was used to determine the relationship that might appear in the study. A statistical significance level of p<0.05 was used for the study. Frequency tables, graphs and charts were used to present the analyzed data. Results showed that a majority of the health facilities had between full and partially implemented EHR systems. The study showed that knowledge in ICT, Education level and healthcare perception were among factors that affected the implementation of EHR systems