Predicting employability in an unstable developing country requires the use of contextual factors... more Predicting employability in an unstable developing country requires the use of contextual factors as predictors and a suitable machine learning model capable of generalization. This study has discovered that parental financial stability, sociopolitical, relationship, academic, and strategic factors are the factors that can contextually predict the employability of information technology (IT) graduates in the democratic republic of Congo (DRC). A deep stacking predictive model was constructed using five different multilayer perceptron (MLP) sub models. The deep stacking model measured good performance (80% accuracy, 0.81 precision, 0.80 recall, 0.77 f1-score). All the individual models could not reach these performances with all the evaluation metrics used. Therefore, deep stacking was revealed to be the most suitable method for building a generalizable model to predict employability of IT graduates in the DRC. The authors estimate that the discovery of these contextual factors that ...
2019 IEEE International Conference on Engineering, Technology and Innovation (ICE/ITMC), 2019
Business organizations in Kenya are classified as small, medium and large. Within these classific... more Business organizations in Kenya are classified as small, medium and large. Within these classifications, there exist structural and operational factors that influence the adoption of information systems (IS), and identifying these factors is crucial to IS implementation. The study conducted a survey of 50 such businesses within Kajiado, a County characterized by under-developed IS infrastructure and a resource scarcity that is typical of many peripheral counties in Kenya. Results are presented in the form of descriptive statistics and a hierarchical regression model. Some of the key variables studies during adoption and diffusion included characteristics of decision-makers, organization, the environment and the IS infrastructure. The results of this study can be used to identify the key variables that drive the adoption of IS in small- and medium-sized businesses. The study therefore provides parties involved with adoption process a practical synopsis of the IS adoption process which is believed to assist them with successful adoption.
This working paper provides a description of the phases of my PhD study. Drawing on assumptions f... more This working paper provides a description of the phases of my PhD study. Drawing on assumptions from various theories of environmental criminology, this study applies various crime mapping methodologies to observe geographic and temporal patterns of crime in the eastern part of the Kenyan capital city, Nairobi. This paper outlines the first completed phase which employs criminal geographic profiling to predict offender abodes, and also briefly identifies the next two phases of the study that involve spatio-temporal analysis and a regression modeling respectively. Results from the completed study have potential implications on the prediction and ultimate reduction of criminality, both within the Nairobi capital and also in other cities with similar spatial patterns.
2021 IEEE International Conference on Engineering, Technology and Innovation (ICE/ITMC), 2021
Land is a vital asset for societal and economic resilience in many developing countries. In Kenya... more Land is a vital asset for societal and economic resilience in many developing countries. In Kenya, the rate of land subdivision has accelerated with the rapid increase in population. Continuous urbanization and availability of arable land in the Njoro urban area of Nakuru county, the study site, have led to fast changes in ownership and land subdivision. This has put immense pressure on the land registry and posed a challenge to landowners wishing to manage their parcels. Socioeconomic and political implications of land ownership make it imperative to innovate a transparent system that will enable users locate their land using GPS, monitor future land subdivision, control fraud in the land registry and store electronic logs of historical land processing. The current research work set out to develop such a mechanism that provides real-time information to landowners, buyers and other stakeholders. The tasks were to map the cadastral map of Njoro area onto a geographic information system (GIS) and allocate each portion of land with a centroid for storing size and location information. Electronic green cards were generated for each parcel for logging land status- and ownership changes. A weighted spatial regression model assessed the factors influencing land subdivision and discovered that proximity to schools, shopping centers and major roads were highly significant. It is expected that results of this research will advise policy formulation in the Kenyan land registry and minimize the fraud and corruption that accompany manual management of land records.
Annals of the American Association of Geographers, 2016
Residential population data are frequently employed to link the crime incidence of an area with t... more Residential population data are frequently employed to link the crime incidence of an area with the number of residents to estimate the underlying risk. Human mobility patterns cause shifts in the baseline population, however, that can potentially influence the crime statistics. This study therefore employed an ambient population that combined residential population data with data depicting the commuting activity in small administrative areas. The effects of the commuter-harmonized ambient population on crime were then evaluated in a series of negative binomial regression models. The models also controlled for criminogenic factors and incorporated eigenvector spatial filtering to adjust for spatial effects. The results show significant effects of commuting patterns on crime outcomes. For certain crimes, such as violence, theft, and disorder, the inbound commuters are significantly associated with high risk. It was further discovered that an offset variable comprising the commuter-harmonized ambient population data models the crime outcomes more reliably than when residential population data are used. Spatial filtering was found to effectively eradicate residual spatial autocorrelation after accounting for effects of the predictor variables. We conclude that calculating crime rates using the residential population does not constitute an accurate risk measure and that the ambient population has crucial implications for realistic and reliable target representation and crime modeling.
International Journal of Engineering Pedagogy (iJEP)
Envisaging an adequate IT/IS solution that can mitigate the employability problems is imperative ... more Envisaging an adequate IT/IS solution that can mitigate the employability problems is imperative because nowadays there is a high rate of unemployed graduates. Thus, the main goal of this systematic literature review (SLR) was to explore the application of data mining techniques in modeling employability and see how those techniques have been applied and which factors/variables have been retained to be the most predictors or/and prescribers of employability. Data mining techniques have shown the ability to serve as decision support tools in predicting and even prescribing employability. The review determined and analyzed the machine learning algorithms used in data mining to either predict or prescribe employability. This review used the PRISMA method to determine which studies from the existing literature to include as items for this SLR. Hence, 20 relevant studies, 16 of which are predicting employability and 4 of which are prescribing employability. These studies were selected fr...
Predicting employability in an unstable developing country requires the use of contextual factors... more Predicting employability in an unstable developing country requires the use of contextual factors as predictors and a suitable machine learning model capable of generalization. This study has discovered that parental financial stability, sociopolitical, relationship, academic, and strategic factors are the factors that can contextually predict the employability of information technology (IT) graduates in the democratic republic of Congo (DRC). A deep stacking predictive model was constructed using five different multilayer perceptron (MLP) sub models. The deep stacking model measured good performance (80% accuracy, 0.81 precision, 0.80 recall, 0.77 f1-score). All the individual models could not reach these performances with all the evaluation metrics used. Therefore, deep stacking was revealed to be the most suitable method for building a generalizable model to predict employability of IT graduates in the DRC. The authors estimate that the discovery of these contextual factors that ...
2019 IEEE International Conference on Engineering, Technology and Innovation (ICE/ITMC), 2019
Business organizations in Kenya are classified as small, medium and large. Within these classific... more Business organizations in Kenya are classified as small, medium and large. Within these classifications, there exist structural and operational factors that influence the adoption of information systems (IS), and identifying these factors is crucial to IS implementation. The study conducted a survey of 50 such businesses within Kajiado, a County characterized by under-developed IS infrastructure and a resource scarcity that is typical of many peripheral counties in Kenya. Results are presented in the form of descriptive statistics and a hierarchical regression model. Some of the key variables studies during adoption and diffusion included characteristics of decision-makers, organization, the environment and the IS infrastructure. The results of this study can be used to identify the key variables that drive the adoption of IS in small- and medium-sized businesses. The study therefore provides parties involved with adoption process a practical synopsis of the IS adoption process which is believed to assist them with successful adoption.
This working paper provides a description of the phases of my PhD study. Drawing on assumptions f... more This working paper provides a description of the phases of my PhD study. Drawing on assumptions from various theories of environmental criminology, this study applies various crime mapping methodologies to observe geographic and temporal patterns of crime in the eastern part of the Kenyan capital city, Nairobi. This paper outlines the first completed phase which employs criminal geographic profiling to predict offender abodes, and also briefly identifies the next two phases of the study that involve spatio-temporal analysis and a regression modeling respectively. Results from the completed study have potential implications on the prediction and ultimate reduction of criminality, both within the Nairobi capital and also in other cities with similar spatial patterns.
2021 IEEE International Conference on Engineering, Technology and Innovation (ICE/ITMC), 2021
Land is a vital asset for societal and economic resilience in many developing countries. In Kenya... more Land is a vital asset for societal and economic resilience in many developing countries. In Kenya, the rate of land subdivision has accelerated with the rapid increase in population. Continuous urbanization and availability of arable land in the Njoro urban area of Nakuru county, the study site, have led to fast changes in ownership and land subdivision. This has put immense pressure on the land registry and posed a challenge to landowners wishing to manage their parcels. Socioeconomic and political implications of land ownership make it imperative to innovate a transparent system that will enable users locate their land using GPS, monitor future land subdivision, control fraud in the land registry and store electronic logs of historical land processing. The current research work set out to develop such a mechanism that provides real-time information to landowners, buyers and other stakeholders. The tasks were to map the cadastral map of Njoro area onto a geographic information system (GIS) and allocate each portion of land with a centroid for storing size and location information. Electronic green cards were generated for each parcel for logging land status- and ownership changes. A weighted spatial regression model assessed the factors influencing land subdivision and discovered that proximity to schools, shopping centers and major roads were highly significant. It is expected that results of this research will advise policy formulation in the Kenyan land registry and minimize the fraud and corruption that accompany manual management of land records.
Annals of the American Association of Geographers, 2016
Residential population data are frequently employed to link the crime incidence of an area with t... more Residential population data are frequently employed to link the crime incidence of an area with the number of residents to estimate the underlying risk. Human mobility patterns cause shifts in the baseline population, however, that can potentially influence the crime statistics. This study therefore employed an ambient population that combined residential population data with data depicting the commuting activity in small administrative areas. The effects of the commuter-harmonized ambient population on crime were then evaluated in a series of negative binomial regression models. The models also controlled for criminogenic factors and incorporated eigenvector spatial filtering to adjust for spatial effects. The results show significant effects of commuting patterns on crime outcomes. For certain crimes, such as violence, theft, and disorder, the inbound commuters are significantly associated with high risk. It was further discovered that an offset variable comprising the commuter-harmonized ambient population data models the crime outcomes more reliably than when residential population data are used. Spatial filtering was found to effectively eradicate residual spatial autocorrelation after accounting for effects of the predictor variables. We conclude that calculating crime rates using the residential population does not constitute an accurate risk measure and that the ambient population has crucial implications for realistic and reliable target representation and crime modeling.
International Journal of Engineering Pedagogy (iJEP)
Envisaging an adequate IT/IS solution that can mitigate the employability problems is imperative ... more Envisaging an adequate IT/IS solution that can mitigate the employability problems is imperative because nowadays there is a high rate of unemployed graduates. Thus, the main goal of this systematic literature review (SLR) was to explore the application of data mining techniques in modeling employability and see how those techniques have been applied and which factors/variables have been retained to be the most predictors or/and prescribers of employability. Data mining techniques have shown the ability to serve as decision support tools in predicting and even prescribing employability. The review determined and analyzed the machine learning algorithms used in data mining to either predict or prescribe employability. This review used the PRISMA method to determine which studies from the existing literature to include as items for this SLR. Hence, 20 relevant studies, 16 of which are predicting employability and 4 of which are prescribing employability. These studies were selected fr...
Uploads