5307 research outputs found
Sort by
Developing an early warning system for Banana Xanthomonas Wilt (BXW) in Rwanda
No full textFull - text thesisBananas are crucial for the agricultural economy of the African Great Lakes region, including countries like Kenya, Uganda, Tanzania, Burundi, Rwanda, and parts of the Democratic Republic of Congo, with an annual production exceeding 22 million tonnes. However, banana productivity faces significant threats from pests and diseases such as the Banana Xanthomonas Wilt (BXW), caused by the bacterium Xanthomonas campestris pv. Musacearum. In this study, machine learning techniques were employed to develop an early warning system for BXW. Various classification models, including Support Vector Machine (SVM), K-Nearest Neighbors (KNN), Random Forest (RF), and Gradient Boosting Machine (GBM), were trained and evaluated for predicting BXW occurrence. RF outperformed the other models with an accuracy of 94%, followed by GBM (89%), KNN (87%), and SVM (83%). In terms of the area under the curve (AUC), RF outperformed the other models with a score of 96%, followed by GBM (95%), KNN (94%), and SVM (90%). This highlights RF’s effectiveness in creating habitat suitability maps and establishing an early warning system for BXW. The RF model was used to develop a BXW habitat suitability map for Rwanda, aiding agricultural stakeholders in identifying high-risk areas. Furthermore, a Short Message Service (SMS)-based early warning system was implemented to provide timely alerts to farmers, thereby, enhancing BXW mitigation efforts. Additionally, a web portal for real-time BXW risk prediction and analysis was developed, providing accessible information to stakeholders for proactive management strategies.
Keywords: BXW, Early Warning System, Rwanda, Remote Sensing, Machine Learning
The Effect of risk management strategies on the organizational performance of oil companies in Kenya
No full textFull - text thesisIn recent years, risk management has become a priority for all sectors of the economy, so organizations can protect their interests while achieving their goals. Through risk management, organizations can ensure that it will achieve the desired results, reduce the impact of threats to acceptable levels, and increase opportunities to seize opportunities. The study was carried out to analyze the impact of risk management strategies on the organizational performance of oil companies in Kenya. The specific objectives were; to establish the effects risk acceptance strategies, risk transfer strategies, risk avoidance strategies and risk reduction strategies on performance of oil companies in Kenya. The study was guided by risk compensation theory and resource-based view. The study sampled 166 respondents from a target population of 284 employees. Data collected was analyzed using SPSS version 22.0. Inferential statistics using multiple regression and correlation analysis was applied to test the relationship between the independent variables and the dependent variable. The results of regression model expressed the hypothesized relationship between variables under study. Correlation analysis was used to determine the nature and magnitude of the relationship among the variables. The findings revealed a high positive relationship between risk acceptance, risk transfer, risk avoidance, risk reduction and organizational performance. The research also revealed that there is a high level of correlation between risk management strategies and organizational performance. The study concluded that effective management of risk is essential for any enterprise since it positively affects organizational performance. The study recommendations were as follows; oil companies should develop strategies to improve on risk management strategies and there should be adequate feasibility studies to bring out all the risks involved at any given time to prepare to mitigation. Lack of cooperation, filling of questionnaires within the stipulated and failure to give information were greatest limitation of the study when collecting data
A Bi-Lingual counselling chatbot application for support of Gender Based Violence victims in Kenya
Get PDFFull - text thesisGender-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 fuelled 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 centres 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 scor
Effect of digital financial services uptake on socio-economic status of households in Kibera
Get PDFFull - text thesisThe current economic conditions characterized by a high cost of living, high interest rates on loans and unemployment, digital lending products and services have increasingly become an option for many. Borrowing appetite has often led to bad debts, shifting between lending institutions to evade the responsibility to repay loans and resulting to debt accumulation. This study sought to find out the influence of digital financial services on the socioeconomic status of Kibera households. Specifically, the research sought to find out: the effect of digital credit services on socioeconomic status of households; the effect of digital savings services on socioeconomic status of households; and the moderating effect of household characteristics on the relationship between digital financial services and socioeconomic status of households. Primary data collection through administering structured questionnaires to the target population of households in Kibera. The questionnaires were issued randomly but purposively to households that used digital credit and digital savings. Descriptive statistics entailed mean and standard deviation were used for analysis. Inferential statistics, particularly regression analysis was conducted. OLS regression model was used to establish the relationship between the independent variables and the dependent variable. Notably, digital credit, digital savings and household characteristics had a positive relationship with socioeconomic status. Digital savings had a positive effect while digital credit reported a negative effect on socioeconomic status. Only one element of household characteristics namely, household size had a moderating effect on the relationship between digital financial services and socioeconomic status. The findings of this study are important to policymakers, regulators and digital financial services providers. The findings will be significant to future researchers who might need to refer or build on it through further research. The study recommended that there was need for policy makers to look at how the negative effects of digital credit on socioeconomic status can be reversed and maximize on the positive impact of digital savings on socioeconomic status of households.
Key Words: Digital Credit, Digital Savings, Socioeconomic status, Household characteristic
Role of emotional intelligence in transgenerational succession among family businesses in Nairobi County
No full textFull - text thesisTransgenerational succession has been a major concern for many businesses within the world due to conflicts between the owners, their families and management teams. This has consistently derailed the operations of the institutions. In Kenya, more than 70% of businesses are family-owned, but only 10%-15% survive past two generations, hence there is need to understand what can help to improve the succession within these family firms. This survey sought to establish the role of emotional intelligence during transgenerational succession in family businesses in Nairobi County. This was studied within the lenses of key emotional intelligence aspects; self-awareness, self-management, social awareness and self-regulation in transgenerational succession in family businesses. The research was premised on the social exchange theory, emotional contagion theory and the family systems theory. The study used a positivist paradigm and a descriptive research design in the investigation. Population of the survey was the registered (530) firms under the Association of Family-Owned Businesses. Purposive sampling was used in the selection of participants with only firms that have undergone transgenerational succession being included in the research. A sample of 228 firms that have gone through succession was considered for the research. A structured research questionnaire was utilized in the data collection with both drop and pick method as well as use of Google forms. The study instrument was pretested to determine its reliability and validity. Analysis of the study data was conducted using descriptive and inferential statistics. The findings showed that there was a weak positive correlation between emotional intelligence (i.e., self-awareness, self-management, social awareness, self-regulation) and transgenerational succession. Regression results revealed that overall, there was a positive and statistically significant relationship between emotional intelligence and transgenerational succession in family businesses. However, the relationship with individual measures of emotional intelligence offered varied results. Self-awareness, self-management and self-regulation had a positive and significant effect on the transgenerational succession in family businesses. On the other hand, social-awareness did not have a significant effect on transgenerational succession in the family businesses studied. Based on these conclusions, the study recommended that family businesses should create a supportive environment where individuals feel comfortable expressing their thoughts and feelings. Additionally, the study recommends that family businesses should prioritize the establishment of clear protocols to facilitate positive resolution of disputes as well as promote trust and confidence among stakeholders during transgenerational succession. The study notes that emotional intelligence may have varying long term effects and therefore recommends longitudinal studies tracking family businesses over multiple generations.
Keywords: Self-Awareness, Self-Management, Social Awareness and Self-Regulation
Factors determining member retention among Deposit-Taking SACCOs and Non-Deposit-Taking SACCOs in Kenya
No full textFull - text thesisThis study presents a comprehensive examination of member retention in Kenya's Savings and Credit Cooperatives (SACCOs), focusing on two distinct types: Deposit-Taking SACCOs (DTS) and Non-Deposit-Taking SACCOs (NDTS). The sustainability and profitability of SACCOs depend heavily on member retention since it guarantees a steady membership base, which is essential to their long-term viability. High member turnover can undermine SACCOs and harm their financial stability because these organizations rely on member contributions for operating support and the supply of financial services. This study is among the first to compare and empirically document the member retention challenges faced by these two types of SACCOs since DTS was regulated in 2010. NDTS was only recently included in the regulatory framework by the Sacco Society Regulatory Authority (SASRA) in 2021. The research objectives were to assess retention levels, establish SACCO organizational factors for member retention strategies in DTS and NDTS, and evaluate management viewpoints on member retention in both DTS and NDTS. The study's theoretical approach was based on common bond, institutional, stakeholder, and agency theories. Using a mixed-methods methodology and positivist and post-positivist ideologies; the study combined quantitative and qualitative data. Cross-sectional data covering 2022 was analyzed using Ordinary Least Squares on data from 176 DTS and 185 NDTS in Kenya. SACCO officials’ questionnaires were used to enhance the data that came from SACCO annual reports. The results showed that while NDTS and DTS exhibited comparable member retention rates, DTS had somewhat higher average rates. The study determined that several factors affected member retention. Profitability was found to have a statistically significant, positive effect, whereas interest rates while hurting retention, were not. Retention rates were surprisingly negatively impacted by asset growth, although asset quality, while negatively correlated, was considered insignificant. The study also demonstrated the importance of corporate governance elements, indicating that while board diversity had no significant effect on member retention, board size had a positive effect. It was found that the most critical component for member retention was the composition of the board. Regulatory impact adversely impacted retention, and capital structure was not significant and hurt member retention. This study advances knowledge of SACCO dynamics in Kenya's financial industry and offers valuable information on member retention tactics and regulatory implications for SACCO management and legislators
A Customer churn prediction and corrective action suggestion model for the telecommunications industry using predictive analytics
Get PDFFull - text thesisThe telecommunications industry is significantly susceptible to customer churn. Customer churn leads to loss of customer base which leads to reduction in revenue, reduced profit margins, increased customer acquisition costs and loss of brand value. Mitigating the effects of customer churn has proved to be a tall order for many organizations in the telecommunications industry. Most companies employ a reactive approach to customer churn and thus do not take any corrective actions until the customer has left. This approach does not enable organizations to know and prevent potential churn before it occurs. Alternatively, some organizations employ a more proactive approach to mitigate customer churn through predictive analytics. Although this approach is more effective, it only predicts which customers will churn without recommending the appropriate corrective action. In this dissertation, a customer churn prediction and corrective action suggestion model using predictive analytics was implemented to predict churn and suggest appropriate corrective actions. The IBM telco customer churn dataset accessed via API from the open machine learning.org website was used for this study. The dataset was subjected to pre-processing and exploratory data analysis to gain valuable insights into the data. To enhance the reliability of the developed model, an 80/20 train/test split was applied to the dataset. The training dataset was then divided into 5 folds before model fitting. Several classification algorithms; Logistic Regression, Gaussian Naive Bayes, Complement Naïve Bayes, K-NN, Random Forest and CatBoost were then fit with the training data and their performance was evaluated. Logistic Regression achieved a recall of 80% and was selected for system implementation. Logistic regression feature coefficients were then used to determine the appropriate corrective actions. A locally hosted web interface was then developed using the Python Streamlit library to enable users to feed input into the model and get churn predictions and corrective action suggestions. The developed model demonstrated ease of use and high performance and will enable telecommunication companies to accurately predict customer attrition and take appropriate corrective actions, reducing customer attrition's impact on the companies’ bottom line.
Keywords: churn, machine learning, predictive analytics, telecommunications industr
Moderating effect of balance of payment position on the drivers of exchange rate volatility in Kenya
No full textFull - text thesisThe volatility of exchange rates is the source of exchange rate risk and has certain implications on the volume of international trade. Exchange rates influence decisions made by individuals, governments, and businesses. Collectively, this affects economic activity, inflation, and the balance of payments. The study sought to establish the effects of market sentiment, information asymmetry, and economic cycles on exchange rate volatility in Kenya, moderated by the balance payment position. The study was supported by the Purchasing Power Parity Theory. It applied a positivist research philosophy while its research design was correlational. Secondary data on the research variables was collected from the Central Bank of Kenya and Bloomberg for ten years between 2014 and 2023 using monthly data a total of 120 observations. This study used EViews12 to conduct descriptive and inferential statistical analysis. According to the findings of the study, Balance of payment was significant as a moderating variable for all the equations and reduced the effect of the independent variable on the dependent variable thus strengthening the Kenya shilling. All regression models indicate that the dependent variable of exchange rates was significantly affected by information asymmetry, economic cycles, and balance of payment. Inflation was introduced as a control variable and was found to be significant in all models. The study adds to the existing body of knowledge on drivers of exchange rate volatility by providing fresh insights through the focus on the moderating effect of balance of payments. Additionally, the interactions amongst market sentiment, information asymmetry, and economic cycles in one single study are unique in terms of their influence on exchange rate volatility, thereby offering useful references to scholars, professionals, and researchers. The study recommended that the Government needs to come up measures to reduced information asymmetry in the economy and find solution to high net imports by encouraging import substitution. These policies should be cognisant of underlying factors such as information asymmetry, economic cycles, and even balance of payments.
Key Terms: Balance of Trade Position, Economic Cycles, Information Asymmetry
The Effect of business growth strategies on organizational performance: a case of tier III commercial banks in Nairobi City County, Kenya
Get PDFFull - text thesisIndustry statistics have shown that continuously Tier-III commercial banks in Kenya have suffered from intense competition within the industry. This has resulted in a drop in the performance of the firms and the placement of several institutions under receivership. Further, most of the Tier III banks have failed to meet the prudential requirements as advanced by the regulator. It is from this backdrop that this research sought to determine if business growth strategies do influence the performance of the banks. The research specifically focused on product development strategies, diversification strategies, market penetration strategies, and market development strategies. The organization performance of the banks was measured using the balance scorecard perspective. The study used both the Ansoff Growth Matrix and the resource-based view to inform how business growth strategies can be leveraged to foster competitiveness and performance within the industry. The research implemented a descriptive cross-sectional design in the conduct of the study. This allowed for the examination of the study variables within a particular period. The population of the study was the 22 operational Tier III banks with 5 senior managers being considered for the study. The sample size for this study was 105 participants drawn from the banks. Structured questionnaires were applied in the data collection. The study analyzed the data using a quantitative approach; descriptive, correlation and regression analysis. The findings were presented using charts and tables. The research obtained a 75% response rate from the selected participants. The correlation tests showed there was positive relation between product development strategies, diversification strategies, market penetration strategies, market development strategies, and organization performance of Tier III commercial banks. Overall, the regression established that 78.5% of changes in the organization performance of Tier III commercial banks in Kenya are determined by the business growth strategies. The coefficient findings showed that market penetration and diversification strategies did have a significant positive influence on organization performance while market development and product development did not significantly impact the banks' performance. The research concluded that business growth strategies have significant positive effects on the organizational performance of Tier III commercial banks in Kenya. Findings also supported the conclusion that only market penetration and diversification strategies had a significant positive effect on the performance of the banks. The study recommends that the bank management constantly review existing products, develop new products, and align product decisions with expected earnings and wealth maximization objectives. The study recommends that the banks adapt digital marketing strategies and strategic partnerships with fintech firms as this would allow them to market services at lower costs and leverage newly developed fintech products. With market development and product development strategies exhibiting insignificant effects on organizational performance, this study calls on Tier III banks to establish unique channels where they can strategically cooperate with customers and industry players in the development of products and services that would cater to market needs
Influence of institutional factors on access to education for children with learning disabilities in public primary schools in Nairobi County
No full textFull - text thesisIn Kenya, basic education is an equal right meant to be enjoyed by everyone. However, most children with disabilities are unable to access this right. This study focused on establishing the influence of institutional factors on access to education for children with learning disabilities in public primary schools in Nairobi County. Based on institutional theory, the study specifically analysed the effect of infrastructure, human resource, management and curriculum factors and how they affect the access to education for children with learning disabilities. A descriptive correlational research design in this study. The sample respondents for the study were 225 principals drawn from public primary schools in Nairobi County. Structured questionnaires were applied in the data collection process with quantitative techniques adopted in the analysis through descriptive and inferential tests. The findings revealed that institutional factors including infrastructural factors, human resources factors, management factors, and curriculum factors had positive correlation with the access of education by the children with disabilities. The study recommends for development and implementation of strategies to improve teacher-student ratios, such as hiring additional staff to provide more individualized support to children with learning disabilities. The study also recommends a strengthening of school management structures to ensure effective coordination and support for initiatives aimed at promoting inclusive education. Finally, the study recommends provision of training and resources for teachers to effectively implement personalized and inclusive teaching methods that accommodate the diverse learning styles and abilities of children with learning disabilities.
Keywords: Physical Disability, Education Access, Curriculum, Human Resource, Infrastructure, Managemen